# Backend gallery: a GENERATED copy of the backend library, # gallery/backends/index.yaml. The library is the source of truth; edit it, not # this file. This file is written by scripts/backends/cmd/backendcatalog and # stays only so releases before the cutover keep working. CI fails when it # differs from the generated copy: # go run ./scripts/backends/cmd/backendcatalog --library gallery/backends/index.yaml --out backend/index.yaml - name: llama-cpp alias: llama-cpp license: mit icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png description: | LLM inference in C/C++ urls: - https://github.com/ggerganov/llama.cpp tags: - text-to-text - text-to-speech - TTS - LLM - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-llama-cpp default: cpu-llama-cpp intel: intel-sycl-f16-llama-cpp metal: metal-llama-cpp nvidia: cuda12-llama-cpp nvidia-cuda-12: cuda12-llama-cpp nvidia-cuda-13: cuda13-llama-cpp nvidia-l4t: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp vulkan: vulkan-llama-cpp - name: ik-llama-cpp alias: ik-llama-cpp license: mit description: | Fork of llama.cpp optimized for CPU performance by ikawrakow urls: - https://github.com/ikawrakow/ik_llama.cpp tags: - text-to-text - LLM - CPU capabilities: default: cpu-ik-llama-cpp - name: turboquant alias: turboquant license: mit description: | Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama. urls: - https://github.com/TheTom/llama-cpp-turboquant tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - turboquant - kv-cache capabilities: amd: rocm-turboquant default: cpu-turboquant intel: intel-sycl-f16-turboquant nvidia: cuda12-turboquant nvidia-cuda-12: cuda12-turboquant nvidia-cuda-13: cuda13-turboquant nvidia-l4t: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant vulkan: vulkan-turboquant - name: bonsai alias: bonsai license: apache-2.0 description: | Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit) weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp backend. urls: - https://github.com/PrismML-Eng/llama.cpp - https://huggingface.co/prism-ml tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - bonsai - 1-bit - ternary capabilities: amd: rocm-bonsai default: cpu-bonsai intel: intel-sycl-f16-bonsai nvidia: cuda12-bonsai nvidia-cuda-12: cuda12-bonsai nvidia-cuda-13: cuda13-bonsai nvidia-l4t: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai vulkan: vulkan-bonsai - name: ds4 alias: ds4 license: mit description: | antirez/ds4 - DeepSeek V4 Flash inference engine. Single-model, optimized for Metal (Darwin) and CUDA (Linux). Requires the GGUFs published at huggingface.co/antirez/deepseek-v4-gguf. urls: - https://github.com/antirez/ds4 tags: - text-to-text - LLM - CPU - CUDA - Metal capabilities: default: cpu-ds4 metal: metal-ds4 metal-darwin-arm64: metal-ds4 nvidia: cuda13-ds4 nvidia-cuda-13: cuda13-ds4 nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ds4 - name: audio-cpp alias: audio-cpp license: apache-2.0 description: | 0xShug0/audio.cpp - a ggml audio inference framework covering text to speech, voice cloning, transcription, forced alignment, voice activity detection, speaker diarization, source separation, voice conversion and music generation, across 30+ model families. Consumes audio.cpp-native GGUF packages from huggingface.co/audio-cpp/audio.cpp-gguf. urls: - https://github.com/0xShug0/audio.cpp - https://huggingface.co/audio-cpp/audio.cpp-gguf tags: - TTS - text-to-speech - audio-transcription - CPU - CUDA - HIP - Metal capabilities: amd: rocm-audio-cpp default: cpu-audio-cpp metal: metal-audio-cpp metal-darwin-arm64: metal-audio-cpp nvidia: cuda12-audio-cpp nvidia-cuda-12: cuda12-audio-cpp nvidia-cuda-13: cuda13-audio-cpp - name: whisper alias: whisper license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | Port of OpenAI's Whisper model in C/C++ urls: - https://github.com/ggml-org/whisper.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-whisper default: cpu-whisper intel: intel-sycl-f16-whisper metal: metal-whisper nvidia: cuda12-whisper nvidia-cuda-12: cuda12-whisper nvidia-cuda-13: cuda13-whisper nvidia-l4t: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper vulkan: vulkan-whisper - name: vllm-cpp alias: vllm-cpp license: apache-2.0 description: | ALPHA development builds. Try it, but llama-cpp stays the recommendation for production use. vllm.cpp is an Apache-2.0 C++20 inference engine maintained by the LocalAI team, developed in its own repository and usable without LocalAI. It began as a port of vLLM and keeps vLLM as its reference implementation, checking output against it and benchmarking against it, while growing a featureset of its own. It implements vLLM's V1 architecture (paged KV cache, continuous batching, prefix caching, scheduler, sampler) on a portable tensor runtime with no Python, PyTorch or ggml at inference time. It loads GGUF as well as Hugging Face safetensors, supports structured output (JSON schema / regex / choice / GBNF grammar) enforced in-engine, ships speculative decoding and KV offload, and runs on CPU, NVIDIA CUDA (Blackwell-family), Apple Metal and Vulkan. The project is expected to be renamed as it diverges further from vLLM; the new name is still to be decided. urls: - https://github.com/mudler/vllm.cpp tags: - text-to-text - LLM - CPU - GPU - CUDA - metal capabilities: default: cpu-vllm-cpp metal: metal-vllm-cpp nvidia: cuda13-vllm-cpp nvidia-cuda-13: cuda13-vllm-cpp nvidia-l4t: nvidia-l4t-arm64-vllm-cpp nvidia-l4t-cuda-13: nvidia-l4t-arm64-vllm-cpp vulkan: vulkan-vllm-cpp - name: vllm-cpp-development alias: vllm-cpp license: apache-2.0 description: | ALPHA development builds. Try it, but llama-cpp stays the recommendation for production use. vllm.cpp is an Apache-2.0 C++20 inference engine maintained by the LocalAI team, developed in its own repository and usable without LocalAI. It began as a port of vLLM and keeps vLLM as its reference implementation, checking output against it and benchmarking against it, while growing a featureset of its own. It implements vLLM's V1 architecture (paged KV cache, continuous batching, prefix caching, scheduler, sampler) on a portable tensor runtime with no Python, PyTorch or ggml at inference time. It loads GGUF as well as Hugging Face safetensors, supports structured output (JSON schema / regex / choice / GBNF grammar) enforced in-engine, ships speculative decoding and KV offload, and runs on CPU, NVIDIA CUDA (Blackwell-family), Apple Metal and Vulkan. The project is expected to be renamed as it diverges further from vLLM; the new name is still to be decided. urls: - https://github.com/mudler/vllm.cpp tags: - text-to-text - LLM - CPU - GPU - CUDA - metal capabilities: default: cpu-vllm-cpp-development metal: metal-vllm-cpp-development nvidia: cuda13-vllm-cpp-development nvidia-cuda-13: cuda13-vllm-cpp-development nvidia-l4t: nvidia-l4t-arm64-vllm-cpp-development nvidia-l4t-cuda-13: nvidia-l4t-arm64-vllm-cpp-development vulkan: vulkan-vllm-cpp-development - name: crispasr alias: crispasr license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more). urls: - https://github.com/CrispStrobe/CrispASR tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-crispasr default: cpu-crispasr intel: intel-sycl-f16-crispasr metal: metal-crispasr nvidia: cuda12-crispasr nvidia-cuda-12: cuda12-crispasr nvidia-cuda-13: cuda13-crispasr nvidia-l4t: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr vulkan: vulkan-crispasr - name: parakeet-cpp alias: parakeet-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models. It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/parakeet.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-parakeet-cpp default: cpu-parakeet-cpp intel: intel-sycl-f16-parakeet-cpp metal: metal-parakeet-cpp nvidia: cuda12-parakeet-cpp nvidia-cuda-12: cuda12-parakeet-cpp nvidia-cuda-13: cuda13-parakeet-cpp nvidia-l4t: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-parakeet-cpp vulkan: vulkan-parakeet-cpp - name: nemo-speech-cpp alias: nemo-speech-cpp license: apache-2.0 icon: https://avatars.githubusercontent.com/u/1728152?s=200&v=4 description: | NVIDIA NeMo-Speech.cpp, a C++/ggml runtime for NVIDIA Nemotron Speech models. One backend serves four model families, selected automatically from the GGUF general.architecture key: automatic speech recognition (offline, cache-aware streaming and live transcription, with optional Silero VAD, punctuation, inverse text normalization and Sortformer speaker diarization attached), standalone Sortformer diarization, MagpieTTS text-to-speech over NanoCodec, and Riva-Translate text translation. Runs on CPU, NVIDIA CUDA, Vulkan, NVIDIA Jetson (L4T) and Apple Metal. urls: - https://github.com/NVIDIA/NeMo-Speech.cpp tags: - audio-transcription - text-to-speech - diarization - text-to-text - CPU - GPU - CUDA - Metal capabilities: default: cpu-nemo-speech-cpp metal: metal-nemo-speech-cpp nvidia: cuda12-nemo-speech-cpp nvidia-cuda-12: cuda12-nemo-speech-cpp nvidia-cuda-13: cuda13-nemo-speech-cpp nvidia-l4t: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-nemo-speech-cpp vulkan: vulkan-nemo-speech-cpp - name: moss-transcribe-cpp alias: moss-transcribe-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | moss-transcribe.cpp is a C++/ggml port of OpenMOSS MOSS-Transcribe-Diarize, an end-to-end audio understanding model. It does joint long-form transcription, speaker diarization and timestamping in a single pass, emitting a speaker-labelled, time-aligned transcript, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan, Apple Metal and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/moss-transcribe.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-moss-transcribe-cpp default: cpu-moss-transcribe-cpp intel: intel-sycl-f16-moss-transcribe-cpp metal: metal-moss-transcribe-cpp nvidia: cuda12-moss-transcribe-cpp nvidia-cuda-12: cuda12-moss-transcribe-cpp nvidia-cuda-13: cuda13-moss-transcribe-cpp nvidia-l4t: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-transcribe-cpp vulkan: vulkan-moss-transcribe-cpp - name: ced alias: ced license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | CED sound-event classification / audio tagging (527-class AudioSet). ced.cpp is a C++/ggml port that performs audio tagging over the AudioSet taxonomy, exposed through the SoundDetection gRPC rpc and the /v1/audio/classification REST endpoint. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/ced.cpp tags: - audio-classification - CPU - GPU - CUDA - HIP capabilities: amd: rocm-ced default: cpu-ced intel: intel-sycl-f16-ced metal: metal-ced nvidia: cuda12-ced nvidia-cuda-12: cuda12-ced nvidia-cuda-13: cuda13-ced nvidia-l4t: nvidia-l4t-arm64-ced nvidia-l4t-cuda-12: nvidia-l4t-arm64-ced nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ced vulkan: vulkan-ced - name: voice-detect alias: voice-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | voice-detect speaker recognition and voice analysis. voice-detect.cpp is a C++/ggml engine that produces L2-normalised speaker embeddings (ECAPA-TDNN, WeSpeaker ResNet34, 3D-Speaker ERes2Net, CAM++) for voice verification and 1:N identification, plus a wav2vec2 age / gender / emotion analysis head. It replaces the Python speaker-recognition backend and is exposed through the Voice* gRPC rpcs and the /v1/voice/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/voice-detect.cpp tags: - voice-recognition - speaker-verification - speaker-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-voice-detect default: cpu-voice-detect intel: intel-sycl-f16-voice-detect metal: metal-voice-detect nvidia: cuda12-voice-detect nvidia-cuda-12: cuda12-voice-detect nvidia-cuda-13: cuda13-voice-detect nvidia-l4t: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-voice-detect vulkan: vulkan-voice-detect - name: face-detect alias: face-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | face-detect face detection, embedding, verification and analysis. face-detect.cpp is a C++/ggml engine that runs SCRFD / YuNet face detection and ArcFace / SFace 512-d (or 128-d) L2-normalised face embeddings for verification and 1:N identification, plus a landmark / age / gender analysis head. It replaces the Python insightface backend and is exposed through the Embedding, Detect and Face* gRPC rpcs and the /v1/face/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/face-detect.cpp tags: - face-recognition - face-verification - face-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-face-detect default: cpu-face-detect intel: intel-sycl-f16-face-detect metal: metal-face-detect nvidia: cuda12-face-detect nvidia-cuda-12: cuda12-face-detect nvidia-cuda-13: cuda13-face-detect nvidia-l4t: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-face-detect vulkan: vulkan-face-detect - name: voxtral alias: voxtral license: mit description: | Voxtral Realtime 4B Pure C speech-to-text inference engine urls: - https://github.com/mudler/voxtral.c tags: - audio-transcription - CPU - Metal capabilities: default: cpu-voxtral metal-darwin-arm64: metal-voxtral - name: stablediffusion-ggml alias: stablediffusion-ggml license: mit icon: https://github.com/leejet/stable-diffusion.cpp/raw/master/assets/cat_with_sd_cpp_42.png description: | Stable Diffusion and Flux in pure C/C++ urls: - https://github.com/leejet/stable-diffusion.cpp tags: - image-generation - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-stablediffusion-ggml default: cpu-stablediffusion-ggml intel: intel-sycl-f16-stablediffusion-ggml metal: metal-stablediffusion-ggml nvidia: cuda12-stablediffusion-ggml nvidia-cuda-12: cuda12-stablediffusion-ggml nvidia-cuda-13: cuda13-stablediffusion-ggml nvidia-l4t: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-12: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-stablediffusion-ggml vulkan: vulkan-stablediffusion-ggml - name: kimodocpp alias: kimodocpp license: apache-2.0 description: | kimodo.cpp text-to-motion: animated skeleton GLB on CPU and Vulkan. Apple Silicon uses the CPU runtime. urls: - https://github.com/localai-org/kimodo.cpp tags: - 3d-animation - text-to-motion - CPU - Vulkan capabilities: amd: vulkan-kimodocpp default: cpu-kimodocpp intel: vulkan-kimodocpp metal: cpu-darwin-arm64-kimodocpp nvidia: vulkan-kimodocpp nvidia-cuda-12: vulkan-kimodocpp nvidia-cuda-13: vulkan-kimodocpp vulkan: vulkan-kimodocpp - name: gemxcpp alias: gemxcpp license: apache-2.0 description: | gem-x.cpp live human motion: SOMA and SMPL pose streams on CPU and Vulkan. Apple Silicon uses the CPU runtime. urls: - https://github.com/localai-org/gem-x.cpp tags: - motion - pose-estimation - CPU - Vulkan capabilities: amd: vulkan-gemxcpp default: cpu-gemxcpp intel: vulkan-gemxcpp metal: cpu-darwin-arm64-gemxcpp nvidia: vulkan-gemxcpp nvidia-cuda-12: vulkan-gemxcpp nvidia-cuda-13: vulkan-gemxcpp vulkan: vulkan-gemxcpp - name: trellis2cpp alias: trellis2cpp license: mit description: | TRELLIS.2 image-to-3D generation (GLB meshes with PBR textures) in C++/ggml urls: - https://github.com/localai-org/trellis2cpp - https://github.com/microsoft/TRELLIS.2 tags: - image-to-3d - 3d-generation - CPU - GPU - CUDA - Metal capabilities: default: cpu-trellis2cpp metal: metal-trellis2cpp nvidia: cuda12-trellis2cpp nvidia-cuda-12: cuda12-trellis2cpp nvidia-cuda-13: cuda13-trellis2cpp nvidia-l4t: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-trellis2cpp vulkan: vulkan-trellis2cpp - name: rfdetr alias: rfdetr license: apache-2.0 icon: https://avatars.githubusercontent.com/u/53104118?s=200&v=4 description: | RF-DETR is a real-time, transformer-based object detection model architecture developed by Roboflow and released under the Apache 2.0 license. RF-DETR is the first real-time model to exceed 60 AP on the Microsoft COCO benchmark alongside competitive performance at base sizes. It also achieves state-of-the-art performance on RF100-VL, an object detection benchmark that measures model domain adaptability to real world problems. RF-DETR is fastest and most accurate for its size when compared current real-time objection models. RF-DETR is small enough to run on the edge using Inference, making it an ideal model for deployments that need both strong accuracy and real-time performance. urls: - https://github.com/roboflow/rf-detr tags: - object-detection - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr intel: intel-rfdetr metal: metal-rfdetr nvidia: cuda12-rfdetr nvidia-cuda-12: cuda12-rfdetr nvidia-cuda-13: cuda13-rfdetr nvidia-l4t: nvidia-l4t-arm64-rfdetr nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr - name: insightface alias: insightface license: mixed description: | Face recognition backend powered by `insightface` (ONNX Runtime). Provides face verification (/v1/face/verify), face analysis (/v1/face/analyze), face embedding (/v1/embeddings), face detection (/v1/detection), and 1:N identification (/v1/face/{register,identify,forget}). Ships two engines in a single image: one that drives the insightface model packs (buffalo_l/s/m/sc, antelopev2 — non-commercial research use only) and one that drives OpenCV Zoo's YuNet + SFace pair (Apache 2.0 — commercial-safe). Select via `options: ["engine:..."]` in your model YAML, or install one of the ready-made model-gallery entries under the `insightface-*` prefix. The backend image contains only code and Python deps; all model weights are managed by LocalAI's gallery download mechanism. urls: - https://github.com/deepinsight/insightface - https://github.com/opencv/opencv_zoo tags: - face-recognition - face-verification - face-embedding - gpu - cpu capabilities: default: cpu-insightface nvidia: cuda12-insightface nvidia-cuda-12: cuda12-insightface - name: sam3-cpp alias: sam3-cpp license: mit description: | Segment Anything Model (SAM 3/2/EdgeTAM) in C/C++ using GGML. Supports text-prompted and point/box-prompted image segmentation. urls: - https://github.com/PABannier/sam3.cpp tags: - image-segmentation - object-detection - sam3 - gpu - cpu capabilities: default: cpu-sam3-cpp intel: intel-sycl-f32-sam3-cpp metal: metal-sam3-cpp nvidia: cuda12-sam3-cpp nvidia-cuda-12: cuda12-sam3-cpp nvidia-cuda-13: cuda13-sam3-cpp nvidia-l4t: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sam3-cpp vulkan: vulkan-sam3-cpp - name: rfdetr-cpp alias: rfdetr-cpp license: apache-2.0 description: | Native RF-DETR object detection and instance segmentation in C/C++ using GGML. Loads pre-built GGUF weights from the mudler/rfdetr-cpp-* family (Nano/Small/Base/Medium/Large + SegNano/SegSmall/SegMedium) and returns bounding boxes, class labels, confidence scores, and (for segmentation variants) PNG-encoded per-detection masks. urls: - https://github.com/localai-org/rf-detr.cpp tags: - object-detection - image-segmentation - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr-cpp intel: intel-sycl-f32-rfdetr-cpp metal: metal-rfdetr-cpp nvidia: cuda12-rfdetr-cpp nvidia-cuda-12: cuda12-rfdetr-cpp nvidia-cuda-13: cuda13-rfdetr-cpp nvidia-l4t: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-rfdetr-cpp vulkan: vulkan-rfdetr-cpp - name: locate-anything alias: locate-anything license: apache-2.0 description: | Open-vocabulary object detection and visual grounding (NVIDIA LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights and, given an image and a free-form text prompt, returns bounding boxes, class labels, and confidence scores for the referred objects. urls: - https://github.com/mudler/locate-anything.cpp - https://huggingface.co/nvidia/LocateAnything-3B tags: - object-detection - visual-grounding - open-vocabulary - locate-anything - gpu - cpu capabilities: default: cpu-locate-anything-cpp intel: intel-sycl-f32-locate-anything-cpp metal: metal-locate-anything-cpp nvidia: cuda12-locate-anything-cpp nvidia-cuda-12: cuda12-locate-anything-cpp nvidia-cuda-13: cuda13-locate-anything-cpp nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp vulkan: vulkan-locate-anything-cpp - name: locate-anything-development alias: locate-anything license: apache-2.0 description: | Open-vocabulary object detection and visual grounding (NVIDIA LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights and, given an image and a free-form text prompt, returns bounding boxes, class labels, and confidence scores for the referred objects. urls: - https://github.com/mudler/locate-anything.cpp - https://huggingface.co/nvidia/LocateAnything-3B tags: - object-detection - visual-grounding - open-vocabulary - locate-anything - gpu - cpu capabilities: default: cpu-locate-anything-cpp-development intel: intel-sycl-f32-locate-anything-cpp-development metal: metal-locate-anything-cpp-development nvidia: cuda12-locate-anything-cpp-development nvidia-cuda-12: cuda12-locate-anything-cpp-development nvidia-cuda-13: cuda13-locate-anything-cpp-development nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp-development nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp-development vulkan: vulkan-locate-anything-cpp-development - name: cpu-locate-anything-cpp alias: locate-anything license: apache-2.0 description: | Open-vocabulary object detection and visual grounding (NVIDIA LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights and, given an image and a free-form text prompt, returns bounding boxes, class labels, and confidence scores for the referred objects. urls: - https://github.com/mudler/locate-anything.cpp - https://huggingface.co/nvidia/LocateAnything-3B tags: - object-detection - visual-grounding - open-vocabulary - locate-anything - gpu - cpu capabilities: default: cpu-locate-anything-cpp intel: intel-sycl-f32-locate-anything-cpp metal: metal-locate-anything-cpp nvidia: cuda12-locate-anything-cpp nvidia-cuda-12: cuda12-locate-anything-cpp nvidia-cuda-13: cuda13-locate-anything-cpp nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp vulkan: vulkan-locate-anything-cpp uri: quay.io/go-skynet/local-ai-backends:latest-cpu-locate-anything-cpp mirrors: - localai/localai-backends:latest-cpu-locate-anything-cpp - name: cpu-locate-anything-cpp-development alias: locate-anything license: apache-2.0 description: | Open-vocabulary object detection and visual grounding (NVIDIA LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights and, given an image and a free-form text prompt, returns bounding boxes, class labels, and confidence scores for the referred objects. urls: - https://github.com/mudler/locate-anything.cpp - https://huggingface.co/nvidia/LocateAnything-3B tags: - object-detection - visual-grounding - open-vocabulary - locate-anything - gpu - cpu capabilities: default: cpu-locate-anything-cpp intel: intel-sycl-f32-locate-anything-cpp metal: metal-locate-anything-cpp nvidia: cuda12-locate-anything-cpp nvidia-cuda-12: cuda12-locate-anything-cpp nvidia-cuda-13: cuda13-locate-anything-cpp nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp vulkan: vulkan-locate-anything-cpp uri: quay.io/go-skynet/local-ai-backends:master-cpu-locate-anything-cpp mirrors: - localai/localai-backends:master-cpu-locate-anything-cpp - name: metal-locate-anything-cpp alias: locate-anything license: apache-2.0 description: | Open-vocabulary object detection and visual grounding (NVIDIA LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights and, given an image and a free-form text prompt, returns bounding boxes, class labels, and confidence scores for the referred objects. urls: - https://github.com/mudler/locate-anything.cpp - https://huggingface.co/nvidia/LocateAnything-3B tags: - object-detection - visual-grounding - open-vocabulary - locate-anything - gpu - cpu capabilities: default: cpu-locate-anything-cpp intel: intel-sycl-f32-locate-anything-cpp metal: metal-locate-anything-cpp nvidia: cuda12-locate-anything-cpp nvidia-cuda-12: cuda12-locate-anything-cpp nvidia-cuda-13: cuda13-locate-anything-cpp nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp vulkan: vulkan-locate-anything-cpp uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-locate-anything-cpp mirrors: - localai/localai-backends:latest-metal-darwin-arm64-locate-anything-cpp - name: metal-locate-anything-cpp-development alias: locate-anything license: apache-2.0 description: | Open-vocabulary object detection and visual grounding (NVIDIA LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights and, given an image and a free-form text prompt, returns bounding boxes, class labels, and confidence scores for the referred objects. urls: - https://github.com/mudler/locate-anything.cpp - https://huggingface.co/nvidia/LocateAnything-3B tags: - object-detection - visual-grounding - open-vocabulary - locate-anything - gpu - cpu capabilities: default: cpu-locate-anything-cpp intel: intel-sycl-f32-locate-anything-cpp metal: metal-locate-anything-cpp nvidia: cuda12-locate-anything-cpp nvidia-cuda-12: cuda12-locate-anything-cpp nvidia-cuda-13: cuda13-locate-anything-cpp nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp vulkan: vulkan-locate-anything-cpp uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-locate-anything-cpp mirrors: - localai/localai-backends:master-metal-darwin-arm64-locate-anything-cpp - name: cuda12-locate-anything-cpp alias: locate-anything license: apache-2.0 description: | Open-vocabulary object detection and visual grounding (NVIDIA LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights and, given an image and a free-form text prompt, returns bounding boxes, class labels, and confidence scores for the referred objects. urls: - https://github.com/mudler/locate-anything.cpp - https://huggingface.co/nvidia/LocateAnything-3B tags: - object-detection - visual-grounding - open-vocabulary - locate-anything - gpu - cpu capabilities: default: cpu-locate-anything-cpp intel: intel-sycl-f32-locate-anything-cpp metal: metal-locate-anything-cpp nvidia: cuda12-locate-anything-cpp nvidia-cuda-12: cuda12-locate-anything-cpp nvidia-cuda-13: cuda13-locate-anything-cpp nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp vulkan: vulkan-locate-anything-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-locate-anything-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-locate-anything-cpp - name: cuda12-locate-anything-cpp-development alias: locate-anything license: apache-2.0 description: | Open-vocabulary object detection and visual grounding (NVIDIA LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights and, given an image and a free-form text prompt, returns bounding boxes, class labels, and confidence scores for the referred objects. urls: - https://github.com/mudler/locate-anything.cpp - https://huggingface.co/nvidia/LocateAnything-3B tags: - object-detection - visual-grounding - open-vocabulary - locate-anything - gpu - cpu capabilities: default: cpu-locate-anything-cpp intel: intel-sycl-f32-locate-anything-cpp metal: metal-locate-anything-cpp nvidia: cuda12-locate-anything-cpp nvidia-cuda-12: cuda12-locate-anything-cpp nvidia-cuda-13: cuda13-locate-anything-cpp nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp vulkan: vulkan-locate-anything-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-locate-anything-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-locate-anything-cpp - name: cuda13-locate-anything-cpp alias: locate-anything license: apache-2.0 description: | Open-vocabulary object detection and visual grounding (NVIDIA LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights and, given an image and a free-form text prompt, returns bounding boxes, class labels, and confidence scores for the referred objects. urls: - https://github.com/mudler/locate-anything.cpp - https://huggingface.co/nvidia/LocateAnything-3B tags: - object-detection - visual-grounding - open-vocabulary - locate-anything - gpu - cpu capabilities: default: cpu-locate-anything-cpp intel: intel-sycl-f32-locate-anything-cpp metal: metal-locate-anything-cpp nvidia: cuda12-locate-anything-cpp nvidia-cuda-12: cuda12-locate-anything-cpp nvidia-cuda-13: cuda13-locate-anything-cpp nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp vulkan: vulkan-locate-anything-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-locate-anything-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-locate-anything-cpp - name: cuda13-locate-anything-cpp-development alias: locate-anything license: apache-2.0 description: | Open-vocabulary object detection and visual grounding (NVIDIA LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights and, given an image and a free-form text prompt, returns bounding boxes, class labels, and confidence scores for the referred objects. urls: - https://github.com/mudler/locate-anything.cpp - https://huggingface.co/nvidia/LocateAnything-3B tags: - object-detection - visual-grounding - open-vocabulary - locate-anything - gpu - cpu capabilities: default: cpu-locate-anything-cpp intel: intel-sycl-f32-locate-anything-cpp metal: metal-locate-anything-cpp nvidia: cuda12-locate-anything-cpp nvidia-cuda-12: cuda12-locate-anything-cpp nvidia-cuda-13: cuda13-locate-anything-cpp nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp vulkan: vulkan-locate-anything-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-locate-anything-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-locate-anything-cpp - name: nvidia-l4t-arm64-locate-anything-cpp alias: locate-anything license: apache-2.0 description: | Open-vocabulary object detection and visual grounding (NVIDIA LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights and, given an image and a free-form text prompt, returns bounding boxes, class labels, and confidence scores for the referred objects. urls: - https://github.com/mudler/locate-anything.cpp - https://huggingface.co/nvidia/LocateAnything-3B tags: - object-detection - visual-grounding - open-vocabulary - locate-anything - gpu - cpu capabilities: default: cpu-locate-anything-cpp intel: intel-sycl-f32-locate-anything-cpp metal: metal-locate-anything-cpp nvidia: cuda12-locate-anything-cpp nvidia-cuda-12: cuda12-locate-anything-cpp nvidia-cuda-13: cuda13-locate-anything-cpp nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp vulkan: vulkan-locate-anything-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-locate-anything-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-arm64-locate-anything-cpp - name: nvidia-l4t-arm64-locate-anything-cpp-development alias: locate-anything license: apache-2.0 description: | Open-vocabulary object detection and visual grounding (NVIDIA LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights and, given an image and a free-form text prompt, returns bounding boxes, class labels, and confidence scores for the referred objects. urls: - https://github.com/mudler/locate-anything.cpp - https://huggingface.co/nvidia/LocateAnything-3B tags: - object-detection - visual-grounding - open-vocabulary - locate-anything - gpu - cpu capabilities: default: cpu-locate-anything-cpp intel: intel-sycl-f32-locate-anything-cpp metal: metal-locate-anything-cpp nvidia: cuda12-locate-anything-cpp nvidia-cuda-12: cuda12-locate-anything-cpp nvidia-cuda-13: cuda13-locate-anything-cpp nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp vulkan: vulkan-locate-anything-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-locate-anything-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-arm64-locate-anything-cpp - name: cuda13-nvidia-l4t-arm64-locate-anything-cpp alias: locate-anything license: apache-2.0 description: | Open-vocabulary object detection and visual grounding (NVIDIA LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights and, given an image and a free-form text prompt, returns bounding boxes, class labels, and confidence scores for the referred objects. urls: - https://github.com/mudler/locate-anything.cpp - https://huggingface.co/nvidia/LocateAnything-3B tags: - object-detection - visual-grounding - open-vocabulary - locate-anything - gpu - cpu capabilities: default: cpu-locate-anything-cpp intel: intel-sycl-f32-locate-anything-cpp metal: metal-locate-anything-cpp nvidia: cuda12-locate-anything-cpp nvidia-cuda-12: cuda12-locate-anything-cpp nvidia-cuda-13: cuda13-locate-anything-cpp nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp vulkan: vulkan-locate-anything-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-locate-anything-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-locate-anything-cpp - name: cuda13-nvidia-l4t-arm64-locate-anything-cpp-development alias: locate-anything license: apache-2.0 description: | Open-vocabulary object detection and visual grounding (NVIDIA LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights and, given an image and a free-form text prompt, returns bounding boxes, class labels, and confidence scores for the referred objects. urls: - https://github.com/mudler/locate-anything.cpp - https://huggingface.co/nvidia/LocateAnything-3B tags: - object-detection - visual-grounding - open-vocabulary - locate-anything - gpu - cpu capabilities: default: cpu-locate-anything-cpp intel: intel-sycl-f32-locate-anything-cpp metal: metal-locate-anything-cpp nvidia: cuda12-locate-anything-cpp nvidia-cuda-12: cuda12-locate-anything-cpp nvidia-cuda-13: cuda13-locate-anything-cpp nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp vulkan: vulkan-locate-anything-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-locate-anything-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-locate-anything-cpp - name: intel-sycl-f32-locate-anything-cpp alias: locate-anything license: apache-2.0 description: | Open-vocabulary object detection and visual grounding (NVIDIA LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights and, given an image and a free-form text prompt, returns bounding boxes, class labels, and confidence scores for the referred objects. urls: - https://github.com/mudler/locate-anything.cpp - https://huggingface.co/nvidia/LocateAnything-3B tags: - object-detection - visual-grounding - open-vocabulary - locate-anything - gpu - cpu capabilities: default: cpu-locate-anything-cpp intel: intel-sycl-f32-locate-anything-cpp metal: metal-locate-anything-cpp nvidia: cuda12-locate-anything-cpp nvidia-cuda-12: cuda12-locate-anything-cpp nvidia-cuda-13: cuda13-locate-anything-cpp nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp vulkan: vulkan-locate-anything-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-locate-anything-cpp mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f32-locate-anything-cpp - name: intel-sycl-f32-locate-anything-cpp-development alias: locate-anything license: apache-2.0 description: | Open-vocabulary object detection and visual grounding (NVIDIA LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights and, given an image and a free-form text prompt, returns bounding boxes, class labels, and confidence scores for the referred objects. urls: - https://github.com/mudler/locate-anything.cpp - https://huggingface.co/nvidia/LocateAnything-3B tags: - object-detection - visual-grounding - open-vocabulary - locate-anything - gpu - cpu capabilities: default: cpu-locate-anything-cpp intel: intel-sycl-f32-locate-anything-cpp metal: metal-locate-anything-cpp nvidia: cuda12-locate-anything-cpp nvidia-cuda-12: cuda12-locate-anything-cpp nvidia-cuda-13: cuda13-locate-anything-cpp nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp vulkan: vulkan-locate-anything-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-locate-anything-cpp mirrors: - localai/localai-backends:master-gpu-intel-sycl-f32-locate-anything-cpp - name: intel-sycl-f16-locate-anything-cpp alias: locate-anything license: apache-2.0 description: | Open-vocabulary object detection and visual grounding (NVIDIA LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights and, given an image and a free-form text prompt, returns bounding boxes, class labels, and confidence scores for the referred objects. urls: - https://github.com/mudler/locate-anything.cpp - https://huggingface.co/nvidia/LocateAnything-3B tags: - object-detection - visual-grounding - open-vocabulary - locate-anything - gpu - cpu capabilities: default: cpu-locate-anything-cpp intel: intel-sycl-f32-locate-anything-cpp metal: metal-locate-anything-cpp nvidia: cuda12-locate-anything-cpp nvidia-cuda-12: cuda12-locate-anything-cpp nvidia-cuda-13: cuda13-locate-anything-cpp nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp vulkan: vulkan-locate-anything-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-locate-anything-cpp mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f16-locate-anything-cpp - name: intel-sycl-f16-locate-anything-cpp-development alias: locate-anything license: apache-2.0 description: | Open-vocabulary object detection and visual grounding (NVIDIA LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights and, given an image and a free-form text prompt, returns bounding boxes, class labels, and confidence scores for the referred objects. urls: - https://github.com/mudler/locate-anything.cpp - https://huggingface.co/nvidia/LocateAnything-3B tags: - object-detection - visual-grounding - open-vocabulary - locate-anything - gpu - cpu capabilities: default: cpu-locate-anything-cpp intel: intel-sycl-f32-locate-anything-cpp metal: metal-locate-anything-cpp nvidia: cuda12-locate-anything-cpp nvidia-cuda-12: cuda12-locate-anything-cpp nvidia-cuda-13: cuda13-locate-anything-cpp nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp vulkan: vulkan-locate-anything-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-locate-anything-cpp mirrors: - localai/localai-backends:master-gpu-intel-sycl-f16-locate-anything-cpp - name: vulkan-locate-anything-cpp alias: locate-anything license: apache-2.0 description: | Open-vocabulary object detection and visual grounding (NVIDIA LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights and, given an image and a free-form text prompt, returns bounding boxes, class labels, and confidence scores for the referred objects. urls: - https://github.com/mudler/locate-anything.cpp - https://huggingface.co/nvidia/LocateAnything-3B tags: - object-detection - visual-grounding - open-vocabulary - locate-anything - gpu - cpu capabilities: default: cpu-locate-anything-cpp intel: intel-sycl-f32-locate-anything-cpp metal: metal-locate-anything-cpp nvidia: cuda12-locate-anything-cpp nvidia-cuda-12: cuda12-locate-anything-cpp nvidia-cuda-13: cuda13-locate-anything-cpp nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp vulkan: vulkan-locate-anything-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-locate-anything-cpp mirrors: - localai/localai-backends:latest-gpu-vulkan-locate-anything-cpp - name: vulkan-locate-anything-cpp-development alias: locate-anything license: apache-2.0 description: | Open-vocabulary object detection and visual grounding (NVIDIA LocateAnything-3B) in C/C++ using GGML. Loads pre-built GGUF weights and, given an image and a free-form text prompt, returns bounding boxes, class labels, and confidence scores for the referred objects. urls: - https://github.com/mudler/locate-anything.cpp - https://huggingface.co/nvidia/LocateAnything-3B tags: - object-detection - visual-grounding - open-vocabulary - locate-anything - gpu - cpu capabilities: default: cpu-locate-anything-cpp intel: intel-sycl-f32-locate-anything-cpp metal: metal-locate-anything-cpp nvidia: cuda12-locate-anything-cpp nvidia-cuda-12: cuda12-locate-anything-cpp nvidia-cuda-13: cuda13-locate-anything-cpp nvidia-l4t: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-locate-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-locate-anything-cpp vulkan: vulkan-locate-anything-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-locate-anything-cpp mirrors: - localai/localai-backends:master-gpu-vulkan-locate-anything-cpp - name: depth-anything alias: depth-anything license: apache-2.0 description: | Depth Anything 3 monocular metric depth + camera pose estimation in C/C++ using GGML. Loads pre-built GGUF weights and, given an image, returns a dense depth map plus the recovered camera extrinsics (3x4) and intrinsics (3x3). No Python at inference (purego, cgo-less). urls: - https://github.com/mudler/depth-anything.cpp - https://huggingface.co/depth-anything/Depth-Anything-V3 tags: - depth-estimation - camera-pose - depth-anything - gpu - cpu capabilities: default: cpu-depth-anything-cpp intel: intel-sycl-f32-depth-anything-cpp metal: metal-depth-anything-cpp nvidia: cuda12-depth-anything-cpp nvidia-cuda-12: cuda12-depth-anything-cpp nvidia-cuda-13: cuda13-depth-anything-cpp nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp vulkan: vulkan-depth-anything-cpp - name: depth-anything-development alias: depth-anything license: apache-2.0 description: | Depth Anything 3 monocular metric depth + camera pose estimation in C/C++ using GGML. Loads pre-built GGUF weights and, given an image, returns a dense depth map plus the recovered camera extrinsics (3x4) and intrinsics (3x3). No Python at inference (purego, cgo-less). urls: - https://github.com/mudler/depth-anything.cpp - https://huggingface.co/depth-anything/Depth-Anything-V3 tags: - depth-estimation - camera-pose - depth-anything - gpu - cpu capabilities: default: cpu-depth-anything-cpp-development intel: intel-sycl-f32-depth-anything-cpp-development metal: metal-depth-anything-cpp-development nvidia: cuda12-depth-anything-cpp-development nvidia-cuda-12: cuda12-depth-anything-cpp-development nvidia-cuda-13: cuda13-depth-anything-cpp-development nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp-development nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp-development vulkan: vulkan-depth-anything-cpp-development - name: cpu-depth-anything-cpp alias: depth-anything license: apache-2.0 description: | Depth Anything 3 monocular metric depth + camera pose estimation in C/C++ using GGML. Loads pre-built GGUF weights and, given an image, returns a dense depth map plus the recovered camera extrinsics (3x4) and intrinsics (3x3). No Python at inference (purego, cgo-less). urls: - https://github.com/mudler/depth-anything.cpp - https://huggingface.co/depth-anything/Depth-Anything-V3 tags: - depth-estimation - camera-pose - depth-anything - gpu - cpu capabilities: default: cpu-depth-anything-cpp intel: intel-sycl-f32-depth-anything-cpp metal: metal-depth-anything-cpp nvidia: cuda12-depth-anything-cpp nvidia-cuda-12: cuda12-depth-anything-cpp nvidia-cuda-13: cuda13-depth-anything-cpp nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp vulkan: vulkan-depth-anything-cpp uri: quay.io/go-skynet/local-ai-backends:latest-cpu-depth-anything-cpp mirrors: - localai/localai-backends:latest-cpu-depth-anything-cpp - name: cpu-depth-anything-cpp-development alias: depth-anything license: apache-2.0 description: | Depth Anything 3 monocular metric depth + camera pose estimation in C/C++ using GGML. Loads pre-built GGUF weights and, given an image, returns a dense depth map plus the recovered camera extrinsics (3x4) and intrinsics (3x3). No Python at inference (purego, cgo-less). urls: - https://github.com/mudler/depth-anything.cpp - https://huggingface.co/depth-anything/Depth-Anything-V3 tags: - depth-estimation - camera-pose - depth-anything - gpu - cpu capabilities: default: cpu-depth-anything-cpp intel: intel-sycl-f32-depth-anything-cpp metal: metal-depth-anything-cpp nvidia: cuda12-depth-anything-cpp nvidia-cuda-12: cuda12-depth-anything-cpp nvidia-cuda-13: cuda13-depth-anything-cpp nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp vulkan: vulkan-depth-anything-cpp uri: quay.io/go-skynet/local-ai-backends:master-cpu-depth-anything-cpp mirrors: - localai/localai-backends:master-cpu-depth-anything-cpp - name: metal-depth-anything-cpp alias: depth-anything license: apache-2.0 description: | Depth Anything 3 monocular metric depth + camera pose estimation in C/C++ using GGML. Loads pre-built GGUF weights and, given an image, returns a dense depth map plus the recovered camera extrinsics (3x4) and intrinsics (3x3). No Python at inference (purego, cgo-less). urls: - https://github.com/mudler/depth-anything.cpp - https://huggingface.co/depth-anything/Depth-Anything-V3 tags: - depth-estimation - camera-pose - depth-anything - gpu - cpu capabilities: default: cpu-depth-anything-cpp intel: intel-sycl-f32-depth-anything-cpp metal: metal-depth-anything-cpp nvidia: cuda12-depth-anything-cpp nvidia-cuda-12: cuda12-depth-anything-cpp nvidia-cuda-13: cuda13-depth-anything-cpp nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp vulkan: vulkan-depth-anything-cpp uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-depth-anything-cpp mirrors: - localai/localai-backends:latest-metal-darwin-arm64-depth-anything-cpp - name: metal-depth-anything-cpp-development alias: depth-anything license: apache-2.0 description: | Depth Anything 3 monocular metric depth + camera pose estimation in C/C++ using GGML. Loads pre-built GGUF weights and, given an image, returns a dense depth map plus the recovered camera extrinsics (3x4) and intrinsics (3x3). No Python at inference (purego, cgo-less). urls: - https://github.com/mudler/depth-anything.cpp - https://huggingface.co/depth-anything/Depth-Anything-V3 tags: - depth-estimation - camera-pose - depth-anything - gpu - cpu capabilities: default: cpu-depth-anything-cpp intel: intel-sycl-f32-depth-anything-cpp metal: metal-depth-anything-cpp nvidia: cuda12-depth-anything-cpp nvidia-cuda-12: cuda12-depth-anything-cpp nvidia-cuda-13: cuda13-depth-anything-cpp nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp vulkan: vulkan-depth-anything-cpp uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-depth-anything-cpp mirrors: - localai/localai-backends:master-metal-darwin-arm64-depth-anything-cpp - name: cuda12-depth-anything-cpp alias: depth-anything license: apache-2.0 description: | Depth Anything 3 monocular metric depth + camera pose estimation in C/C++ using GGML. Loads pre-built GGUF weights and, given an image, returns a dense depth map plus the recovered camera extrinsics (3x4) and intrinsics (3x3). No Python at inference (purego, cgo-less). urls: - https://github.com/mudler/depth-anything.cpp - https://huggingface.co/depth-anything/Depth-Anything-V3 tags: - depth-estimation - camera-pose - depth-anything - gpu - cpu capabilities: default: cpu-depth-anything-cpp intel: intel-sycl-f32-depth-anything-cpp metal: metal-depth-anything-cpp nvidia: cuda12-depth-anything-cpp nvidia-cuda-12: cuda12-depth-anything-cpp nvidia-cuda-13: cuda13-depth-anything-cpp nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp vulkan: vulkan-depth-anything-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-depth-anything-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-depth-anything-cpp - name: cuda12-depth-anything-cpp-development alias: depth-anything license: apache-2.0 description: | Depth Anything 3 monocular metric depth + camera pose estimation in C/C++ using GGML. Loads pre-built GGUF weights and, given an image, returns a dense depth map plus the recovered camera extrinsics (3x4) and intrinsics (3x3). No Python at inference (purego, cgo-less). urls: - https://github.com/mudler/depth-anything.cpp - https://huggingface.co/depth-anything/Depth-Anything-V3 tags: - depth-estimation - camera-pose - depth-anything - gpu - cpu capabilities: default: cpu-depth-anything-cpp intel: intel-sycl-f32-depth-anything-cpp metal: metal-depth-anything-cpp nvidia: cuda12-depth-anything-cpp nvidia-cuda-12: cuda12-depth-anything-cpp nvidia-cuda-13: cuda13-depth-anything-cpp nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp vulkan: vulkan-depth-anything-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-depth-anything-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-depth-anything-cpp - name: cuda13-depth-anything-cpp alias: depth-anything license: apache-2.0 description: | Depth Anything 3 monocular metric depth + camera pose estimation in C/C++ using GGML. Loads pre-built GGUF weights and, given an image, returns a dense depth map plus the recovered camera extrinsics (3x4) and intrinsics (3x3). No Python at inference (purego, cgo-less). urls: - https://github.com/mudler/depth-anything.cpp - https://huggingface.co/depth-anything/Depth-Anything-V3 tags: - depth-estimation - camera-pose - depth-anything - gpu - cpu capabilities: default: cpu-depth-anything-cpp intel: intel-sycl-f32-depth-anything-cpp metal: metal-depth-anything-cpp nvidia: cuda12-depth-anything-cpp nvidia-cuda-12: cuda12-depth-anything-cpp nvidia-cuda-13: cuda13-depth-anything-cpp nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp vulkan: vulkan-depth-anything-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-depth-anything-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-depth-anything-cpp - name: cuda13-depth-anything-cpp-development alias: depth-anything license: apache-2.0 description: | Depth Anything 3 monocular metric depth + camera pose estimation in C/C++ using GGML. Loads pre-built GGUF weights and, given an image, returns a dense depth map plus the recovered camera extrinsics (3x4) and intrinsics (3x3). No Python at inference (purego, cgo-less). urls: - https://github.com/mudler/depth-anything.cpp - https://huggingface.co/depth-anything/Depth-Anything-V3 tags: - depth-estimation - camera-pose - depth-anything - gpu - cpu capabilities: default: cpu-depth-anything-cpp intel: intel-sycl-f32-depth-anything-cpp metal: metal-depth-anything-cpp nvidia: cuda12-depth-anything-cpp nvidia-cuda-12: cuda12-depth-anything-cpp nvidia-cuda-13: cuda13-depth-anything-cpp nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp vulkan: vulkan-depth-anything-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-depth-anything-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-depth-anything-cpp - name: nvidia-l4t-arm64-depth-anything-cpp alias: depth-anything license: apache-2.0 description: | Depth Anything 3 monocular metric depth + camera pose estimation in C/C++ using GGML. Loads pre-built GGUF weights and, given an image, returns a dense depth map plus the recovered camera extrinsics (3x4) and intrinsics (3x3). No Python at inference (purego, cgo-less). urls: - https://github.com/mudler/depth-anything.cpp - https://huggingface.co/depth-anything/Depth-Anything-V3 tags: - depth-estimation - camera-pose - depth-anything - gpu - cpu capabilities: default: cpu-depth-anything-cpp intel: intel-sycl-f32-depth-anything-cpp metal: metal-depth-anything-cpp nvidia: cuda12-depth-anything-cpp nvidia-cuda-12: cuda12-depth-anything-cpp nvidia-cuda-13: cuda13-depth-anything-cpp nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp vulkan: vulkan-depth-anything-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-depth-anything-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-arm64-depth-anything-cpp - name: nvidia-l4t-arm64-depth-anything-cpp-development alias: depth-anything license: apache-2.0 description: | Depth Anything 3 monocular metric depth + camera pose estimation in C/C++ using GGML. Loads pre-built GGUF weights and, given an image, returns a dense depth map plus the recovered camera extrinsics (3x4) and intrinsics (3x3). No Python at inference (purego, cgo-less). urls: - https://github.com/mudler/depth-anything.cpp - https://huggingface.co/depth-anything/Depth-Anything-V3 tags: - depth-estimation - camera-pose - depth-anything - gpu - cpu capabilities: default: cpu-depth-anything-cpp intel: intel-sycl-f32-depth-anything-cpp metal: metal-depth-anything-cpp nvidia: cuda12-depth-anything-cpp nvidia-cuda-12: cuda12-depth-anything-cpp nvidia-cuda-13: cuda13-depth-anything-cpp nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp vulkan: vulkan-depth-anything-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-depth-anything-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-arm64-depth-anything-cpp - name: cuda13-nvidia-l4t-arm64-depth-anything-cpp alias: depth-anything license: apache-2.0 description: | Depth Anything 3 monocular metric depth + camera pose estimation in C/C++ using GGML. Loads pre-built GGUF weights and, given an image, returns a dense depth map plus the recovered camera extrinsics (3x4) and intrinsics (3x3). No Python at inference (purego, cgo-less). urls: - https://github.com/mudler/depth-anything.cpp - https://huggingface.co/depth-anything/Depth-Anything-V3 tags: - depth-estimation - camera-pose - depth-anything - gpu - cpu capabilities: default: cpu-depth-anything-cpp intel: intel-sycl-f32-depth-anything-cpp metal: metal-depth-anything-cpp nvidia: cuda12-depth-anything-cpp nvidia-cuda-12: cuda12-depth-anything-cpp nvidia-cuda-13: cuda13-depth-anything-cpp nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp vulkan: vulkan-depth-anything-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-depth-anything-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-depth-anything-cpp - name: cuda13-nvidia-l4t-arm64-depth-anything-cpp-development alias: depth-anything license: apache-2.0 description: | Depth Anything 3 monocular metric depth + camera pose estimation in C/C++ using GGML. Loads pre-built GGUF weights and, given an image, returns a dense depth map plus the recovered camera extrinsics (3x4) and intrinsics (3x3). No Python at inference (purego, cgo-less). urls: - https://github.com/mudler/depth-anything.cpp - https://huggingface.co/depth-anything/Depth-Anything-V3 tags: - depth-estimation - camera-pose - depth-anything - gpu - cpu capabilities: default: cpu-depth-anything-cpp intel: intel-sycl-f32-depth-anything-cpp metal: metal-depth-anything-cpp nvidia: cuda12-depth-anything-cpp nvidia-cuda-12: cuda12-depth-anything-cpp nvidia-cuda-13: cuda13-depth-anything-cpp nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp vulkan: vulkan-depth-anything-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-depth-anything-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-depth-anything-cpp - name: intel-sycl-f32-depth-anything-cpp alias: depth-anything license: apache-2.0 description: | Depth Anything 3 monocular metric depth + camera pose estimation in C/C++ using GGML. Loads pre-built GGUF weights and, given an image, returns a dense depth map plus the recovered camera extrinsics (3x4) and intrinsics (3x3). No Python at inference (purego, cgo-less). urls: - https://github.com/mudler/depth-anything.cpp - https://huggingface.co/depth-anything/Depth-Anything-V3 tags: - depth-estimation - camera-pose - depth-anything - gpu - cpu capabilities: default: cpu-depth-anything-cpp intel: intel-sycl-f32-depth-anything-cpp metal: metal-depth-anything-cpp nvidia: cuda12-depth-anything-cpp nvidia-cuda-12: cuda12-depth-anything-cpp nvidia-cuda-13: cuda13-depth-anything-cpp nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp vulkan: vulkan-depth-anything-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-depth-anything-cpp mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f32-depth-anything-cpp - name: intel-sycl-f32-depth-anything-cpp-development alias: depth-anything license: apache-2.0 description: | Depth Anything 3 monocular metric depth + camera pose estimation in C/C++ using GGML. Loads pre-built GGUF weights and, given an image, returns a dense depth map plus the recovered camera extrinsics (3x4) and intrinsics (3x3). No Python at inference (purego, cgo-less). urls: - https://github.com/mudler/depth-anything.cpp - https://huggingface.co/depth-anything/Depth-Anything-V3 tags: - depth-estimation - camera-pose - depth-anything - gpu - cpu capabilities: default: cpu-depth-anything-cpp intel: intel-sycl-f32-depth-anything-cpp metal: metal-depth-anything-cpp nvidia: cuda12-depth-anything-cpp nvidia-cuda-12: cuda12-depth-anything-cpp nvidia-cuda-13: cuda13-depth-anything-cpp nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp vulkan: vulkan-depth-anything-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-depth-anything-cpp mirrors: - localai/localai-backends:master-gpu-intel-sycl-f32-depth-anything-cpp - name: intel-sycl-f16-depth-anything-cpp alias: depth-anything license: apache-2.0 description: | Depth Anything 3 monocular metric depth + camera pose estimation in C/C++ using GGML. Loads pre-built GGUF weights and, given an image, returns a dense depth map plus the recovered camera extrinsics (3x4) and intrinsics (3x3). No Python at inference (purego, cgo-less). urls: - https://github.com/mudler/depth-anything.cpp - https://huggingface.co/depth-anything/Depth-Anything-V3 tags: - depth-estimation - camera-pose - depth-anything - gpu - cpu capabilities: default: cpu-depth-anything-cpp intel: intel-sycl-f32-depth-anything-cpp metal: metal-depth-anything-cpp nvidia: cuda12-depth-anything-cpp nvidia-cuda-12: cuda12-depth-anything-cpp nvidia-cuda-13: cuda13-depth-anything-cpp nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp vulkan: vulkan-depth-anything-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-depth-anything-cpp mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f16-depth-anything-cpp - name: intel-sycl-f16-depth-anything-cpp-development alias: depth-anything license: apache-2.0 description: | Depth Anything 3 monocular metric depth + camera pose estimation in C/C++ using GGML. Loads pre-built GGUF weights and, given an image, returns a dense depth map plus the recovered camera extrinsics (3x4) and intrinsics (3x3). No Python at inference (purego, cgo-less). urls: - https://github.com/mudler/depth-anything.cpp - https://huggingface.co/depth-anything/Depth-Anything-V3 tags: - depth-estimation - camera-pose - depth-anything - gpu - cpu capabilities: default: cpu-depth-anything-cpp intel: intel-sycl-f32-depth-anything-cpp metal: metal-depth-anything-cpp nvidia: cuda12-depth-anything-cpp nvidia-cuda-12: cuda12-depth-anything-cpp nvidia-cuda-13: cuda13-depth-anything-cpp nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp vulkan: vulkan-depth-anything-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-depth-anything-cpp mirrors: - localai/localai-backends:master-gpu-intel-sycl-f16-depth-anything-cpp - name: vulkan-depth-anything-cpp alias: depth-anything license: apache-2.0 description: | Depth Anything 3 monocular metric depth + camera pose estimation in C/C++ using GGML. Loads pre-built GGUF weights and, given an image, returns a dense depth map plus the recovered camera extrinsics (3x4) and intrinsics (3x3). No Python at inference (purego, cgo-less). urls: - https://github.com/mudler/depth-anything.cpp - https://huggingface.co/depth-anything/Depth-Anything-V3 tags: - depth-estimation - camera-pose - depth-anything - gpu - cpu capabilities: default: cpu-depth-anything-cpp intel: intel-sycl-f32-depth-anything-cpp metal: metal-depth-anything-cpp nvidia: cuda12-depth-anything-cpp nvidia-cuda-12: cuda12-depth-anything-cpp nvidia-cuda-13: cuda13-depth-anything-cpp nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp vulkan: vulkan-depth-anything-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-depth-anything-cpp mirrors: - localai/localai-backends:latest-gpu-vulkan-depth-anything-cpp - name: vulkan-depth-anything-cpp-development alias: depth-anything license: apache-2.0 description: | Depth Anything 3 monocular metric depth + camera pose estimation in C/C++ using GGML. Loads pre-built GGUF weights and, given an image, returns a dense depth map plus the recovered camera extrinsics (3x4) and intrinsics (3x3). No Python at inference (purego, cgo-less). urls: - https://github.com/mudler/depth-anything.cpp - https://huggingface.co/depth-anything/Depth-Anything-V3 tags: - depth-estimation - camera-pose - depth-anything - gpu - cpu capabilities: default: cpu-depth-anything-cpp intel: intel-sycl-f32-depth-anything-cpp metal: metal-depth-anything-cpp nvidia: cuda12-depth-anything-cpp nvidia-cuda-12: cuda12-depth-anything-cpp nvidia-cuda-13: cuda13-depth-anything-cpp nvidia-l4t: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-depth-anything-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-depth-anything-cpp vulkan: vulkan-depth-anything-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-depth-anything-cpp mirrors: - localai/localai-backends:master-gpu-vulkan-depth-anything-cpp - name: vllm alias: vllm license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM is a fast and easy-to-use library for LLM inference and serving. Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry. vLLM is fast with: State-of-the-art serving throughput Efficient management of attention key and value memory with PagedAttention Continuous batching of incoming requests Fast model execution with CUDA/HIP graph Quantizations: GPTQ, AWQ, AutoRound, INT4, INT8, and FP8 Optimized CUDA kernels, including integration with FlashAttention and FlashInfer Speculative decoding Chunked prefill urls: - https://github.com/vllm-project/vllm tags: - text-to-text - multimodal - GPTQ - AWQ - AutoRound - INT4 - INT8 - FP8 capabilities: amd: rocm-vllm cpu: cpu-vllm intel: intel-vllm metal: metal-vllm nvidia: cuda12-vllm nvidia-cuda-12: cuda12-vllm nvidia-cuda-13: cuda13-vllm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm - name: sglang alias: sglang license: apache-2.0 icon: https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png description: | SGLang is a fast serving framework for large language models and vision language models. It co-designs the backend runtime (RadixAttention, continuous batching, structured decoding) and the frontend language to make interaction with models faster and more controllable. Features include fast backend runtime, flexible frontend language, extensive model support, and an active community. urls: - https://github.com/sgl-project/sglang tags: - text-to-text - multimodal capabilities: amd: rocm-sglang cpu: cpu-sglang intel: intel-sglang nvidia: cuda12-sglang nvidia-cuda-12: cuda12-sglang nvidia-cuda-13: cuda13-sglang nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sglang - name: vllm-omni alias: vllm-omni license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM-Omni is a unified interface for multimodal generation with vLLM. It supports image generation (text-to-image, image editing), video generation (text-to-video, image-to-video), text generation with multimodal inputs, and text-to-speech generation. Only supports NVIDIA (CUDA) and ROCm platforms. urls: - https://github.com/vllm-project/vllm-omni tags: - text-to-image - image-generation - text-to-video - video-generation - text-to-speech - TTS - multimodal - LLM capabilities: amd: rocm-vllm-omni nvidia: cuda12-vllm-omni nvidia-cuda-12: cuda12-vllm-omni nvidia-cuda-13: cuda13-vllm-omni nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm-omni - name: longcat-video alias: longcat-video license: mit icon: https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/main/assets/longcat-video_logo.svg description: | LongCat-Video generation for text, image, and audio-conditioned avatars. Supports LongCat-Video and LongCat-Video-Avatar-1.5, including multi-segment talking-head continuation and an SDPA path for NVIDIA Blackwell ARM64 systems. Requires Linux with an NVIDIA CUDA GPU; CPU, ROCm, and macOS are unsupported. urls: - https://github.com/meituan-longcat/LongCat-Video tags: - text-to-video - image-to-video - audio-to-video - avatar-generation - video-generation - CUDA capabilities: nvidia: cuda12-longcat-video nvidia-cuda-12: cuda12-longcat-video nvidia-cuda-13: cuda13-longcat-video nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-longcat-video - name: mlx license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run LLMs with MLX urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX capabilities: default: cpu-mlx metal: metal-mlx nvidia: cuda12-mlx nvidia-cuda-12: cuda12-mlx nvidia-cuda-13: cuda13-mlx nvidia-l4t: nvidia-l4t-mlx nvidia-l4t-cuda-12: nvidia-l4t-mlx nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx - name: mlx-video license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Generate videos with LTX-2 and converted Wan2.1/Wan2.2 checkpoints using MLX on Apple Silicon. urls: - https://github.com/Blaizzy/mlx-video tags: - text-to-video - image-to-video - MLX capabilities: metal: metal-mlx-video - name: mlx-vlm license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Vision-Language Models with MLX urls: - https://github.com/Blaizzy/mlx-vlm tags: - text-to-text - multimodal - vision-language - LLM - MLX capabilities: default: cpu-mlx-vlm metal: metal-mlx-vlm nvidia: cuda12-mlx-vlm nvidia-cuda-12: cuda12-mlx-vlm nvidia-cuda-13: cuda13-mlx-vlm nvidia-l4t: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm - name: mlx-audio license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Audio Models with MLX urls: - https://github.com/Blaizzy/mlx-audio tags: - audio-to-text - audio-generation - text-to-audio - LLM - MLX capabilities: default: cpu-mlx-audio metal: metal-mlx-audio nvidia: cuda12-mlx-audio nvidia-cuda-12: cuda12-mlx-audio nvidia-cuda-13: cuda13-mlx-audio nvidia-l4t: nvidia-l4t-mlx-audio nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio - name: mlx-distributed license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run distributed LLM inference with MLX across multiple Apple Silicon Macs urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX - distributed capabilities: default: cpu-mlx-distributed metal: metal-mlx-distributed nvidia: cuda12-mlx-distributed nvidia-cuda-12: cuda12-mlx-distributed nvidia-cuda-13: cuda13-mlx-distributed nvidia-l4t: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed - name: rerankers alias: rerankers capabilities: amd: rocm-rerankers intel: intel-rerankers metal: metal-rerankers nvidia: cuda12-rerankers - name: tinygrad alias: tinygrad license: MIT description: | tinygrad is a minimalist deep-learning framework with zero runtime dependencies that targets CUDA, ROCm, Metal, WebGPU and CPU (CLANG). The LocalAI tinygrad backend exposes a single multimodal runtime that covers LLM text generation (Llama / Qwen / Mistral via safetensors or GGUF) with native tool-call extraction, BERT-family embeddings, Stable Diffusion 1.x / 2 / XL image generation, and Whisper speech-to-text. Single image: tinygrad generates its own GPU kernels and dlopens the host driver libraries at runtime, so there is no per-toolkit build split. The same image runs CPU-only or accelerates against CUDA / ROCm / Metal when the host driver is visible. urls: - https://github.com/tinygrad/tinygrad tags: - text-to-text - LLM - embeddings - image-generation - transcription - multimodal uri: quay.io/go-skynet/local-ai-backends:latest-tinygrad mirrors: - localai/localai-backends:latest-tinygrad - name: transformers alias: transformers license: apache-2.0 icon: https://avatars.githubusercontent.com/u/25720743?s=200&v=4 description: | Transformers acts as the model-definition framework for state-of-the-art machine learning models in text, computer vision, audio, video, and multimodal model, for both inference and training. It centralizes the model definition so that this definition is agreed upon across the ecosystem. transformers is the pivot across frameworks: if a model definition is supported, it will be compatible with the majority of training frameworks (Axolotl, Unsloth, DeepSpeed, FSDP, PyTorch-Lightning, ...), inference engines (vLLM, SGLang, TGI, ...), and adjacent modeling libraries (llama.cpp, mlx, ...) which leverage the model definition from transformers. urls: - https://github.com/huggingface/transformers tags: - text-to-text - multimodal capabilities: amd: rocm-transformers intel: intel-transformers metal: metal-transformers nvidia: cuda12-transformers nvidia-cuda-12: cuda12-transformers nvidia-cuda-13: cuda13-transformers - name: diffusers alias: diffusers license: apache-2.0 icon: https://raw.githubusercontent.com/huggingface/diffusers/main/docs/source/en/imgs/diffusers_library.jpg description: "\U0001F917 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules. Whether you're looking for a simple inference solution or training your own diffusion models, \U0001F917 Diffusers is a modular toolbox that supports both.\n" urls: - https://github.com/huggingface/diffusers tags: - image-generation - video-generation - sound-generation - diffusion-models capabilities: amd: rocm-diffusers default: cpu-diffusers intel: intel-diffusers metal: metal-diffusers nvidia: cuda12-diffusers nvidia-cuda-12: cuda12-diffusers nvidia-cuda-13: cuda13-diffusers nvidia-l4t: nvidia-l4t-diffusers nvidia-l4t-cuda-12: nvidia-l4t-diffusers nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-diffusers - name: ace-step alias: ace-step description: | ACE-Step 1.5 is an open-source music generation model. It supports simple mode (natural language description) and advanced mode (caption, lyrics, think, bpm, keyscale, etc.). Uses in-process acestep (LLMHandler for metadata, DiT for audio). urls: - https://github.com/ace-step/ACE-Step-1.5 tags: - music-generation - sound-generation capabilities: amd: rocm-ace-step default: cpu-ace-step intel: intel-ace-step metal: metal-ace-step nvidia: cuda12-ace-step nvidia-cuda-12: cuda12-ace-step nvidia-cuda-13: cuda13-ace-step - name: ace-step-development alias: ace-step description: | ACE-Step 1.5 is an open-source music generation model. It supports simple mode (natural language description) and advanced mode (caption, lyrics, think, bpm, keyscale, etc.). Uses in-process acestep (LLMHandler for metadata, DiT for audio). urls: - https://github.com/ace-step/ACE-Step-1.5 tags: - music-generation - sound-generation capabilities: amd: rocm-ace-step-development default: cpu-ace-step-development intel: intel-ace-step-development metal: metal-ace-step-development nvidia: cuda12-ace-step-development nvidia-cuda-12: cuda12-ace-step-development nvidia-cuda-13: cuda13-ace-step-development - name: acestep-cpp alias: acestep-cpp description: | ACE-Step 1.5 C++ backend using GGML. Native C++ implementation of ACE-Step music generation with GPU support through GGML backends. Generates stereo 48kHz audio from text descriptions and optional lyrics via a two-stage pipeline: text-to-code (ace-qwen3 LLM) + code-to-audio (DiT-VAE). urls: - https://github.com/ace-step/acestep.cpp tags: - music-generation - sound-generation capabilities: amd: rocm-acestep-cpp default: cpu-acestep-cpp intel: intel-sycl-f16-acestep-cpp metal: metal-acestep-cpp nvidia: cuda12-acestep-cpp nvidia-cuda-12: cuda12-acestep-cpp nvidia-cuda-13: cuda13-acestep-cpp nvidia-l4t: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-acestep-cpp vulkan: vulkan-acestep-cpp - name: qwen3-tts-cpp alias: qwen3-tts-cpp description: | Qwen3-TTS C++ backend using GGML (qwentts.cpp). Native C++ text-to-speech with streaming output, named speakers, voice design, and zero-shot voice cloning. 24kHz mono, 11 languages with Mandarin dialects. 0.6B and 1.7B models in Q8_0 / Q4_K_M. urls: - https://github.com/ServeurpersoCom/qwentts.cpp tags: - text-to-speech - tts - voice-cloning - streaming capabilities: amd: rocm-qwen3-tts-cpp default: cpu-qwen3-tts-cpp intel: intel-sycl-f16-qwen3-tts-cpp metal: metal-qwen3-tts-cpp nvidia: cuda12-qwen3-tts-cpp nvidia-cuda-12: cuda12-qwen3-tts-cpp nvidia-cuda-13: cuda13-qwen3-tts-cpp nvidia-l4t: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen3-tts-cpp vulkan: vulkan-qwen3-tts-cpp - name: moss-tts-cpp alias: moss-tts-cpp description: | MOSS-TTS C++ backend using GGML (moss-tts.cpp). Native C++ text-to-speech for the OpenMOSS MOSS-TTS-Local Transformer v1.5 model (a GPT-J local transformer + MOSS-Audio-Tokenizer-v2 neural codec), running from a self-contained GGUF with no Python at inference time. 48kHz stereo output with reference-audio voice cloning. urls: - https://github.com/mudler/moss-tts.cpp - https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF tags: - text-to-speech - tts - voice-cloning capabilities: amd: rocm-moss-tts-cpp default: cpu-moss-tts-cpp intel: intel-sycl-f16-moss-tts-cpp metal: metal-moss-tts-cpp nvidia: cuda12-moss-tts-cpp nvidia-cuda-12: cuda12-moss-tts-cpp nvidia-cuda-13: cuda13-moss-tts-cpp nvidia-l4t: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-tts-cpp vulkan: vulkan-moss-tts-cpp - name: moss-tts-cpp-development alias: moss-tts-cpp description: | MOSS-TTS C++ backend using GGML (moss-tts.cpp). Native C++ text-to-speech for the OpenMOSS MOSS-TTS-Local Transformer v1.5 model (a GPT-J local transformer + MOSS-Audio-Tokenizer-v2 neural codec), running from a self-contained GGUF with no Python at inference time. 48kHz stereo output with reference-audio voice cloning. urls: - https://github.com/mudler/moss-tts.cpp - https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF tags: - text-to-speech - tts - voice-cloning capabilities: amd: rocm-moss-tts-cpp-development default: cpu-moss-tts-cpp-development intel: intel-sycl-f16-moss-tts-cpp-development metal: metal-moss-tts-cpp-development nvidia: cuda12-moss-tts-cpp-development nvidia-cuda-12: cuda12-moss-tts-cpp-development nvidia-cuda-13: cuda13-moss-tts-cpp-development nvidia-l4t: nvidia-l4t-arm64-moss-tts-cpp-development nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-tts-cpp-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-tts-cpp-development vulkan: vulkan-moss-tts-cpp-development - name: magpie-tts-cpp alias: magpie-tts-cpp description: | Magpie TTS C++ backend using GGML (magpie-tts.cpp). Native C++ text-to-speech for NVIDIA's Magpie TTS Multilingual 357M model (encoder + autoregressive decoder over NanoCodec tokens), running from a single self-contained GGUF (model, codec, tokenizer, G2P dictionaries) with no Python at inference time. 22.05kHz mono output, 5 baked voices (Aria, Jason, John, Leo, Sofia), 9+ languages. urls: - https://github.com/mudler/magpie-tts.cpp - https://huggingface.co/mudler/magpie-tts.cpp-gguf tags: - text-to-speech - tts capabilities: amd: rocm-magpie-tts-cpp default: cpu-magpie-tts-cpp intel: intel-sycl-f16-magpie-tts-cpp metal: metal-magpie-tts-cpp nvidia: cuda12-magpie-tts-cpp nvidia-cuda-12: cuda12-magpie-tts-cpp nvidia-cuda-13: cuda13-magpie-tts-cpp nvidia-l4t: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-magpie-tts-cpp vulkan: vulkan-magpie-tts-cpp - name: magpie-tts-cpp-development alias: magpie-tts-cpp description: | Magpie TTS C++ backend using GGML (magpie-tts.cpp). Native C++ text-to-speech for NVIDIA's Magpie TTS Multilingual 357M model (encoder + autoregressive decoder over NanoCodec tokens), running from a single self-contained GGUF (model, codec, tokenizer, G2P dictionaries) with no Python at inference time. 22.05kHz mono output, 5 baked voices (Aria, Jason, John, Leo, Sofia), 9+ languages. urls: - https://github.com/mudler/magpie-tts.cpp - https://huggingface.co/mudler/magpie-tts.cpp-gguf tags: - text-to-speech - tts capabilities: amd: rocm-magpie-tts-cpp-development default: cpu-magpie-tts-cpp-development intel: intel-sycl-f16-magpie-tts-cpp-development metal: metal-magpie-tts-cpp-development nvidia: cuda12-magpie-tts-cpp-development nvidia-cuda-12: cuda12-magpie-tts-cpp-development nvidia-cuda-13: cuda13-magpie-tts-cpp-development nvidia-l4t: nvidia-l4t-arm64-magpie-tts-cpp-development nvidia-l4t-cuda-12: nvidia-l4t-arm64-magpie-tts-cpp-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-magpie-tts-cpp-development vulkan: vulkan-magpie-tts-cpp-development - name: omnivoice-cpp alias: omnivoice-cpp description: | OmniVoice C++ backend using GGML. Native text-to-speech with voice cloning (reference audio + transcript) and voice design (attribute keywords: gender, age, pitch, style, volume, emotion). 24kHz mono output, 646 languages. Supports streaming synthesis. urls: - https://github.com/ServeurpersoCom/omnivoice.cpp tags: - text-to-speech - tts - voice-cloning - voice-design capabilities: amd: rocm-omnivoice-cpp default: cpu-omnivoice-cpp intel: intel-sycl-f16-omnivoice-cpp metal: metal-omnivoice-cpp nvidia: cuda12-omnivoice-cpp nvidia-cuda-12: cuda12-omnivoice-cpp nvidia-cuda-13: cuda13-omnivoice-cpp nvidia-l4t: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-omnivoice-cpp vulkan: vulkan-omnivoice-cpp - name: vibevoice-cpp alias: vibevoice-cpp description: | vibevoice.cpp C++ backend using GGML. Native C++ port of Microsoft VibeVoice for both text-to-speech (with voice cloning via voice prompt GGUFs) and long-form ASR with speaker diarization. Outputs 24kHz mono WAV; ASR returns per-speaker JSON segments. urls: - https://github.com/mudler/vibevoice.cpp tags: - text-to-speech - tts - speech-to-text - asr - voice-cloning - diarization capabilities: amd: rocm-vibevoice-cpp default: cpu-vibevoice-cpp intel: intel-sycl-f16-vibevoice-cpp metal: metal-vibevoice-cpp nvidia: cuda12-vibevoice-cpp nvidia-cuda-12: cuda12-vibevoice-cpp nvidia-cuda-13: cuda13-vibevoice-cpp nvidia-l4t: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice-cpp vulkan: vulkan-vibevoice-cpp - name: localvqe alias: localvqe license: apache2 description: | LocalVQE C++ backend using GGML — joint acoustic echo cancellation, noise suppression, and dereverberation (DeepVQE-style architecture). 16 kHz mono in / out, supports both batch and low-latency streaming. Implements the audio-transform capability. urls: - https://github.com/localai-org/LocalVQE tags: - audio-transform - aec - acoustic-echo-cancellation - noise-suppression - dereverberation capabilities: amd: vulkan-localvqe default: cpu-localvqe intel: vulkan-localvqe metal: metal-localvqe nvidia: vulkan-localvqe nvidia-cuda-12: vulkan-localvqe nvidia-cuda-13: vulkan-localvqe nvidia-l4t: vulkan-localvqe nvidia-l4t-cuda-12: vulkan-localvqe nvidia-l4t-cuda-13: vulkan-localvqe vulkan: vulkan-localvqe - name: privacy-filter alias: privacy-filter license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/5fd5e18a90b6dc4633f6d292/QPiv8pt4JNxr0FdGnpFef.png description: | Standalone GGML engine (privacy-filter.cpp) for the OpenMed privacy-filter PII/NER token-classification model family. It runs the openai-privacy-filter architecture (a gpt-oss-style sparse-MoE bidirectional token classifier) on stock upstream GGML — no llama.cpp coupling and no Python — and serves the TokenClassify RPC (constrained BIOES Viterbi decode into UTF-8 byte-offset entity spans) used by LocalAI's NER PII redaction tier. urls: - https://github.com/localai-org/privacy-filter.cpp tags: - token-classification - ner - pii - privacy - CPU - GPU capabilities: amd: vulkan-privacy-filter default: cpu-privacy-filter intel: vulkan-privacy-filter metal: metal-privacy-filter nvidia: vulkan-privacy-filter nvidia-cuda-12: vulkan-privacy-filter nvidia-cuda-13: cuda13-privacy-filter vulkan: vulkan-privacy-filter - name: faster-whisper license: MIT icon: https://avatars.githubusercontent.com/u/1520500?s=200&v=4 description: | faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models. This implementation is up to 4 times faster than openai/whisper for the same accuracy while using less memory. The efficiency can be further improved with 8-bit quantization on both CPU and GPU. urls: - https://github.com/SYSTRAN/faster-whisper tags: - speech-to-text - Whisper capabilities: amd: rocm-faster-whisper default: cpu-faster-whisper intel: intel-faster-whisper metal: metal-faster-whisper nvidia: cuda12-faster-whisper nvidia-cuda-12: cuda12-faster-whisper nvidia-cuda-13: cuda13-faster-whisper nvidia-l4t: nvidia-l4t-arm64-faster-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-faster-whisper - name: whisper-medusa alias: whisper-medusa license: MIT description: | Whisper-Medusa accelerates Whisper transcription by predicting multiple tokens per decoding step. The upstream checkpoints use custom Transformers generation code and accept audio clips up to 30 seconds. urls: - https://github.com/aiola-lab/whisper-medusa - https://huggingface.co/collections/aiola/whisper-medusa tags: - speech-to-text - transcription - Whisper - Medusa capabilities: default: cpu-whisper-medusa nvidia: cuda12-whisper-medusa nvidia-cuda-12: cuda12-whisper-medusa - name: moonshine alias: moonshine license: MIT description: | Moonshine is a fast, accurate, and efficient speech-to-text transcription model using ONNX Runtime. It provides real-time transcription capabilities with support for multiple model sizes and GPU acceleration. urls: - https://github.com/moonshine-ai/moonshine tags: - speech-to-text - transcription - ONNX capabilities: default: cpu-moonshine metal: metal-moonshine nvidia: cuda12-moonshine nvidia-cuda-12: cuda12-moonshine nvidia-cuda-13: cuda13-moonshine - name: whisperx alias: whisperx license: BSD-4-Clause description: | WhisperX provides fast automatic speech recognition with word-level timestamps, speaker diarization, and forced alignment. Built on faster-whisper and pyannote-audio for high-accuracy transcription with speaker identification. urls: - https://github.com/m-bain/whisperX tags: - speech-to-text - diarization - whisperx capabilities: default: cpu-whisperx metal: metal-whisperx nvidia: cuda12-whisperx nvidia-cuda-12: cuda12-whisperx nvidia-cuda-13: cuda13-whisperx nvidia-l4t: nvidia-l4t-arm64-whisperx nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisperx - name: kokoro alias: kokoro license: apache-2.0 icon: https://avatars.githubusercontent.com/u/166769057?v=4 description: | Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects. urls: - https://huggingface.co/hexgrad/Kokoro-82M - https://github.com/hexgrad/kokoro tags: - text-to-speech - TTS - LLM capabilities: amd: rocm-kokoro default: cpu-kokoro intel: intel-kokoro metal: metal-kokoro nvidia: cuda12-kokoro nvidia-cuda-12: cuda12-kokoro nvidia-cuda-13: cuda13-kokoro nvidia-l4t: nvidia-l4t-kokoro nvidia-l4t-cuda-12: nvidia-l4t-kokoro - name: kokoros alias: kokoros license: apache-2.0 icon: https://avatars.githubusercontent.com/u/166769057?v=4 description: | Kokoros is a pure Rust TTS backend using the Kokoro ONNX model (82M parameters). It provides fast, high-quality text-to-speech with streaming support, built on ONNX Runtime for efficient CPU inference. Supports English, Japanese, Mandarin Chinese, and German. urls: - https://huggingface.co/hexgrad/Kokoro-82M - https://github.com/lucasjinreal/Kokoros tags: - text-to-speech - TTS - Rust - ONNX capabilities: default: cpu-kokoros - name: coqui alias: coqui license: mpl-2.0 icon: https://avatars.githubusercontent.com/u/1338804?s=200&v=4 description: "\U0001F438 Coqui TTS is a library for advanced Text-to-Speech generation.\n\n\U0001F680 Pretrained models in +1100 languages.\n\n\U0001F6E0️ Tools for training new models and fine-tuning existing models in any language.\n\n\U0001F4DA Utilities for dataset analysis and curation.\n" urls: - https://github.com/idiap/coqui-ai-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-coqui intel: intel-coqui metal: metal-coqui nvidia: cuda12-coqui nvidia-cuda-12: cuda12-coqui - name: outetts alias: outetts license: apache-2.0 description: | OuteTTS is an open-weight text-to-speech model from OuteAI (OuteAI/OuteTTS-0.3-1B). Supports custom speaker voices via audio path or default speakers. urls: - https://github.com/OuteAI/outetts tags: - text-to-speech - TTS capabilities: default: cpu-outetts nvidia-cuda-12: cuda12-outetts - name: chatterbox alias: chatterbox license: MIT icon: https://avatars.githubusercontent.com/u/49844015?s=200&v=4 description: | Resemble AI's first production-grade open source TTS model. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs, and is consistently preferred in side-by-side evaluations. Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. It's also the first open source TTS model to support emotion exaggeration control, a powerful feature that makes your voices stand out. urls: - https://github.com/resemble-ai/chatterbox tags: - text-to-speech - TTS capabilities: default: cpu-chatterbox metal: metal-chatterbox nvidia: cuda12-chatterbox nvidia-cuda-12: cuda12-chatterbox nvidia-cuda-13: cuda13-chatterbox nvidia-l4t: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-12: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-chatterbox - name: vibevoice alias: vibevoice license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VibeVoice-Realtime is a real-time text-to-speech model that generates natural-sounding speech. urls: - https://github.com/microsoft/VibeVoice tags: - text-to-speech - TTS capabilities: amd: rocm-vibevoice default: cpu-vibevoice intel: intel-vibevoice metal: metal-vibevoice nvidia: cuda12-vibevoice nvidia-cuda-12: cuda12-vibevoice nvidia-cuda-13: cuda13-vibevoice nvidia-l4t: nvidia-l4t-vibevoice nvidia-l4t-cuda-12: nvidia-l4t-vibevoice nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice - name: qwen-tts alias: qwen-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-TTS is a high-quality text-to-speech model supporting custom voice, voice design, and voice cloning. urls: - https://github.com/QwenLM/Qwen3-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-qwen-tts default: cpu-qwen-tts intel: intel-qwen-tts metal: metal-qwen-tts nvidia: cuda12-qwen-tts nvidia-cuda-12: cuda12-qwen-tts nvidia-cuda-13: cuda13-qwen-tts nvidia-l4t: nvidia-l4t-qwen-tts nvidia-l4t-cuda-12: nvidia-l4t-qwen-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-tts - name: fish-speech alias: fish-speech license: apache-2.0 icon: https://avatars.githubusercontent.com/u/148526220?s=200&v=4 description: | Fish Speech is a high-quality text-to-speech model supporting voice cloning via reference audio. urls: - https://github.com/fishaudio/fish-speech tags: - text-to-speech - TTS - voice-cloning capabilities: amd: rocm-fish-speech default: cpu-fish-speech intel: intel-fish-speech nvidia: cuda12-fish-speech nvidia-cuda-12: cuda12-fish-speech nvidia-cuda-13: cuda13-fish-speech nvidia-l4t: nvidia-l4t-fish-speech nvidia-l4t-cuda-12: nvidia-l4t-fish-speech nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-fish-speech - name: faster-qwen3-tts alias: faster-qwen3-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Real-time Qwen3-TTS inference using CUDA graph capture. Voice clone only; requires NVIDIA GPU with CUDA. urls: - https://github.com/andimarafioti/faster-qwen3-tts - https://pypi.org/project/faster-qwen3-tts/ tags: - text-to-speech - TTS - voice-clone capabilities: default: cuda12-faster-qwen3-tts nvidia: cuda12-faster-qwen3-tts nvidia-cuda-12: cuda12-faster-qwen3-tts nvidia-cuda-13: cuda13-faster-qwen3-tts nvidia-l4t: nvidia-l4t-faster-qwen3-tts nvidia-l4t-cuda-12: nvidia-l4t-faster-qwen3-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-faster-qwen3-tts - name: funasr alias: funasr license: mit icon: https://avatars.githubusercontent.com/u/109454077 description: | FunASR is an industrial-grade speech recognition toolkit supporting 50+ languages. Includes SenseVoice (170x realtime, emotion detection), Paraformer (highest Chinese accuracy), and built-in VAD, punctuation restoration, and speaker diarization. urls: - https://github.com/modelscope/FunASR tags: - speech-recognition - ASR - multilingual capabilities: amd: rocm-funasr default: cpu-funasr intel: intel-funasr metal: metal-funasr nvidia: cuda12-funasr nvidia-cuda-12: cuda12-funasr nvidia-cuda-13: cuda13-funasr nvidia-l4t: nvidia-l4t-funasr nvidia-l4t-cuda-12: nvidia-l4t-funasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-funasr - name: qwen-asr alias: qwen-asr license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-ASR is an automatic speech recognition model supporting multiple languages and batch inference. urls: - https://github.com/QwenLM/Qwen3-ASR tags: - speech-recognition - ASR capabilities: amd: rocm-qwen-asr default: cpu-qwen-asr intel: intel-qwen-asr metal: metal-qwen-asr nvidia: cuda12-qwen-asr nvidia-cuda-12: cuda12-qwen-asr nvidia-cuda-13: cuda13-qwen-asr nvidia-l4t: nvidia-l4t-qwen-asr nvidia-l4t-cuda-12: nvidia-l4t-qwen-asr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-asr - name: nemo alias: nemo license: apache-2.0 icon: https://www.nvidia.com/favicon.ico description: | NVIDIA NEMO Toolkit for ASR provides state-of-the-art automatic speech recognition models including Parakeet models for various languages and use cases. urls: - https://github.com/NVIDIA/NeMo tags: - speech-recognition - ASR - NVIDIA capabilities: amd: rocm-nemo default: cpu-nemo intel: intel-nemo metal: metal-nemo nvidia: cuda12-nemo nvidia-cuda-12: cuda12-nemo nvidia-cuda-13: cuda13-nemo - name: voxcpm alias: voxcpm license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech. urls: - https://github.com/ModelBest/VoxCPM tags: - text-to-speech - TTS capabilities: amd: rocm-voxcpm default: cpu-voxcpm intel: intel-voxcpm metal: metal-voxcpm nvidia: cuda12-voxcpm nvidia-cuda-12: cuda12-voxcpm nvidia-cuda-13: cuda13-voxcpm - name: pocket-tts alias: pocket-tts license: mit icon: https://avatars.githubusercontent.com/u/151010778?s=200&v=4 description: | Pocket TTS is a lightweight text-to-speech model designed to run efficiently on CPUs. urls: - https://github.com/kyutai-labs/pocket-tts tags: - text-to-speech - TTS capabilities: amd: rocm-pocket-tts default: cpu-pocket-tts intel: intel-pocket-tts metal: metal-pocket-tts nvidia: cuda12-pocket-tts nvidia-cuda-12: cuda12-pocket-tts nvidia-cuda-13: cuda13-pocket-tts nvidia-l4t: nvidia-l4t-pocket-tts nvidia-l4t-cuda-12: nvidia-l4t-pocket-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-pocket-tts - name: piper license: MIT icon: https://github.com/OHF-Voice/piper1-gpl/raw/main/etc/logo.png description: | A fast, local neural text to speech system urls: - https://github.com/rhasspy/piper - https://github.com/mudler/go-piper tags: - text-to-speech - TTS capabilities: default: cpu-piper metal: metal-piper - name: opus alias: opus license: BSD-3-Clause description: | Opus audio codec backend for encoding and decoding audio. Required for WebRTC transport in the Realtime API. urls: - https://opus-codec.org/ tags: - audio-codec - opus - WebRTC - realtime capabilities: default: cpu-opus metal: metal-opus - name: opus-development alias: opus license: BSD-3-Clause description: | Opus audio codec backend for encoding and decoding audio. Required for WebRTC transport in the Realtime API. urls: - https://opus-codec.org/ tags: - audio-codec - opus - WebRTC - realtime capabilities: default: cpu-opus-development metal: metal-opus-development - name: silero-vad icon: https://user-images.githubusercontent.com/12515440/89997349-b3523080-dc94-11ea-9906-ca2e8bc50535.png description: | Silero VAD: pre-trained enterprise-grade Voice Activity Detector. Silero VAD is a voice activity detection model that can be used to detect whether a given audio contains speech or not. urls: - https://github.com/snakers4/silero-vad tags: - voice-activity-detection - VAD - silero-vad - CPU capabilities: default: cpu-silero-vad metal: metal-silero-vad - name: local-store license: MIT description: | Local Store is a local-first, self-hosted, and open-source vector database. urls: - https://github.com/mudler/LocalAI tags: - vector-database - local-first - open-source - CPU capabilities: default: cpu-local-store metal: metal-local-store - name: cloud-proxy alias: cloud-proxy license: MIT description: | Forward OpenAI-compatible and Anthropic chat requests to external providers. urls: - https://github.com/mudler/LocalAI/tree/master/backend/go/cloud-proxy tags: - text-to-text - cloud - proxy - CPU capabilities: default: cpu-cloud-proxy metal: metal-cloud-proxy - name: localai-proxy alias: localai-proxy license: MIT description: | Serve a model from another LocalAI instance: text, embeddings, rerank, audio, image and video requests are forwarded to its REST API. urls: - https://github.com/mudler/LocalAI/tree/master/backend/go/localai-proxy tags: - text-to-text - proxy - CPU capabilities: default: cpu-localai-proxy metal: metal-localai-proxy - name: valkey-store license: MIT description: | Valkey Store is a Valkey Search (FT.*) backed vector store for LocalAI. It persists vectors across restarts and supports opt-in HNSW indexing. Requires a reachable Valkey Search server (valkey/valkey-bundle). urls: - https://github.com/mudler/LocalAI tags: - vector-database - valkey - open-source - CPU capabilities: default: cpu-valkey-store metal: metal-valkey-store - name: qdrant-store license: MIT description: | Qdrant Store is a Qdrant-backed vector store for LocalAI. It persists vectors across restarts in HNSW-indexed collections and works with self-hosted Qdrant (single node or cluster) and Qdrant Cloud. Requires a reachable Qdrant server (gRPC port, 6334 by default). urls: - https://github.com/mudler/LocalAI - https://github.com/qdrant/qdrant tags: - vector-database - qdrant - open-source - CPU capabilities: default: cpu-qdrant-store metal: metal-qdrant-store - name: kitten-tts license: apache-2.0 description: | Kitten TTS is a text-to-speech model that can generate speech from text. urls: - https://github.com/KittenML/KittenTTS tags: - text-to-speech - TTS capabilities: default: cpu-kitten-tts metal: metal-kitten-tts - name: neutts license: apache-2.0 description: | NeuTTS Air is the world’s first super-realistic, on-device, TTS speech language model with instant voice cloning. Built off a 0.5B LLM backbone, NeuTTS Air brings natural-sounding speech, real-time performance, built-in security and speaker cloning to your local device - unlocking a new category of embedded voice agents, assistants, toys, and compliance-safe apps. urls: - https://github.com/neuphonic/neutts-air tags: - text-to-speech - TTS capabilities: amd: rocm-neutts default: cpu-neutts nvidia: cuda12-neutts nvidia-cuda-12: cuda12-neutts - name: sherpa-onnx alias: sherpa-onnx description: | Sherpa-ONNX backend for text-to-speech (VITS, Matcha, Kokoro), speech-to-text (Whisper, Paraformer, SenseVoice, Omnilingual ASR CTC), and voice activity detection via ONNX Runtime. Supports multi-speaker voices, 1600+ language ASR, and GPU acceleration. urls: - https://k2-fsa.github.io/sherpa/onnx/ tags: - text-to-speech - TTS - speech-to-text - ASR capabilities: default: cpu-sherpa-onnx metal: metal-sherpa-onnx nvidia: cuda12-sherpa-onnx nvidia-cuda-12: cuda12-sherpa-onnx - name: supertonic alias: supertonic description: | Supertonic backend: lightning-fast, on-device multilingual text-to-speech via ONNX Runtime. Runs Supertone's flow-matching TTS model (Supertone/supertonic-3), 44.1kHz output, 31 languages, multiple preset voice styles. No espeak-ng dependency. urls: - https://github.com/supertone-inc/supertonic tags: - text-to-speech - TTS capabilities: default: cpu-supertonic metal: metal-supertonic - name: neutts-development license: apache-2.0 description: | NeuTTS Air is the world’s first super-realistic, on-device, TTS speech language model with instant voice cloning. Built off a 0.5B LLM backbone, NeuTTS Air brings natural-sounding speech, real-time performance, built-in security and speaker cloning to your local device - unlocking a new category of embedded voice agents, assistants, toys, and compliance-safe apps. urls: - https://github.com/neuphonic/neutts-air tags: - text-to-speech - TTS capabilities: amd: rocm-neutts-development default: cpu-neutts-development nvidia: cuda12-neutts-development nvidia-cuda-12: cuda12-neutts-development - name: llama-cpp-development alias: llama-cpp license: mit icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png description: | LLM inference in C/C++ urls: - https://github.com/ggerganov/llama.cpp tags: - text-to-text - text-to-speech - TTS - LLM - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-llama-cpp-development default: cpu-llama-cpp-development intel: intel-sycl-f16-llama-cpp-development metal: metal-llama-cpp-development nvidia: cuda12-llama-cpp-development nvidia-cuda-12: cuda12-llama-cpp-development nvidia-cuda-13: cuda13-llama-cpp-development nvidia-l4t: nvidia-l4t-arm64-llama-cpp-development nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp-development vulkan: vulkan-llama-cpp-development - name: ik-llama-cpp-development alias: ik-llama-cpp license: mit description: | Fork of llama.cpp optimized for CPU performance by ikawrakow urls: - https://github.com/ikawrakow/ik_llama.cpp tags: - text-to-text - LLM - CPU capabilities: default: cpu-ik-llama-cpp-development - name: turboquant-development alias: turboquant license: mit description: | Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama. urls: - https://github.com/TheTom/llama-cpp-turboquant tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - turboquant - kv-cache capabilities: amd: rocm-turboquant-development default: cpu-turboquant-development intel: intel-sycl-f16-turboquant-development nvidia: cuda12-turboquant-development nvidia-cuda-12: cuda12-turboquant-development nvidia-cuda-13: cuda13-turboquant-development nvidia-l4t: nvidia-l4t-arm64-turboquant-development nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant-development vulkan: vulkan-turboquant-development - name: bonsai-development alias: bonsai license: apache-2.0 description: | Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit) weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp backend. urls: - https://github.com/PrismML-Eng/llama.cpp - https://huggingface.co/prism-ml tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - bonsai - 1-bit - ternary capabilities: amd: rocm-bonsai-development default: cpu-bonsai-development intel: intel-sycl-f16-bonsai-development nvidia: cuda12-bonsai-development nvidia-cuda-12: cuda12-bonsai-development nvidia-cuda-13: cuda13-bonsai-development nvidia-l4t: nvidia-l4t-arm64-bonsai-development nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai-development vulkan: vulkan-bonsai-development - name: ds4-development alias: ds4 license: mit description: | antirez/ds4 - DeepSeek V4 Flash inference engine. Single-model, optimized for Metal (Darwin) and CUDA (Linux). Requires the GGUFs published at huggingface.co/antirez/deepseek-v4-gguf. urls: - https://github.com/antirez/ds4 tags: - text-to-text - LLM - CPU - CUDA - Metal capabilities: default: cpu-ds4-development metal: metal-ds4-development metal-darwin-arm64: metal-ds4-development nvidia: cuda13-ds4-development nvidia-cuda-13: cuda13-ds4-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ds4-development - name: audio-cpp-development alias: audio-cpp license: apache-2.0 description: | 0xShug0/audio.cpp - a ggml audio inference framework covering text to speech, voice cloning, transcription, forced alignment, voice activity detection, speaker diarization, source separation, voice conversion and music generation, across 30+ model families. Consumes audio.cpp-native GGUF packages from huggingface.co/audio-cpp/audio.cpp-gguf. urls: - https://github.com/0xShug0/audio.cpp - https://huggingface.co/audio-cpp/audio.cpp-gguf tags: - TTS - text-to-speech - audio-transcription - CPU - CUDA - HIP - Metal capabilities: amd: rocm-audio-cpp-development default: cpu-audio-cpp-development metal: metal-audio-cpp-development metal-darwin-arm64: metal-audio-cpp-development nvidia: cuda12-audio-cpp-development nvidia-cuda-12: cuda12-audio-cpp-development nvidia-cuda-13: cuda13-audio-cpp-development - name: stablediffusion-ggml-development alias: stablediffusion-ggml license: mit icon: https://github.com/leejet/stable-diffusion.cpp/raw/master/assets/cat_with_sd_cpp_42.png description: | Stable Diffusion and Flux in pure C/C++ urls: - https://github.com/leejet/stable-diffusion.cpp tags: - image-generation - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-stablediffusion-ggml-development default: cpu-stablediffusion-ggml-development intel: intel-sycl-f16-stablediffusion-ggml-development metal: metal-stablediffusion-ggml-development nvidia: cuda12-stablediffusion-ggml-development nvidia-cuda-12: cuda12-stablediffusion-ggml-development nvidia-cuda-13: cuda13-stablediffusion-ggml-development nvidia-l4t: nvidia-l4t-arm64-stablediffusion-ggml-development nvidia-l4t-cuda-12: nvidia-l4t-arm64-stablediffusion-ggml-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-stablediffusion-ggml-development vulkan: vulkan-stablediffusion-ggml-development - name: trellis2cpp-development alias: trellis2cpp license: mit description: | TRELLIS.2 image-to-3D generation (GLB meshes with PBR textures) in C++/ggml urls: - https://github.com/localai-org/trellis2cpp - https://github.com/microsoft/TRELLIS.2 tags: - image-to-3d - 3d-generation - CPU - GPU - CUDA - Metal capabilities: default: cpu-trellis2cpp-development metal: metal-trellis2cpp-development nvidia: cuda12-trellis2cpp-development nvidia-cuda-12: cuda12-trellis2cpp-development nvidia-cuda-13: cuda13-trellis2cpp-development nvidia-l4t: nvidia-l4t-arm64-trellis2cpp-development nvidia-l4t-cuda-12: nvidia-l4t-arm64-trellis2cpp-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-trellis2cpp-development vulkan: vulkan-trellis2cpp-development - name: cpu-neutts license: apache-2.0 description: | NeuTTS Air is the world’s first super-realistic, on-device, TTS speech language model with instant voice cloning. Built off a 0.5B LLM backbone, NeuTTS Air brings natural-sounding speech, real-time performance, built-in security and speaker cloning to your local device - unlocking a new category of embedded voice agents, assistants, toys, and compliance-safe apps. urls: - https://github.com/neuphonic/neutts-air tags: - text-to-speech - TTS capabilities: amd: rocm-neutts default: cpu-neutts nvidia: cuda12-neutts nvidia-cuda-12: cuda12-neutts uri: quay.io/go-skynet/local-ai-backends:latest-cpu-neutts mirrors: - localai/localai-backends:latest-cpu-neutts - name: cuda12-neutts license: apache-2.0 description: | NeuTTS Air is the world’s first super-realistic, on-device, TTS speech language model with instant voice cloning. Built off a 0.5B LLM backbone, NeuTTS Air brings natural-sounding speech, real-time performance, built-in security and speaker cloning to your local device - unlocking a new category of embedded voice agents, assistants, toys, and compliance-safe apps. urls: - https://github.com/neuphonic/neutts-air tags: - text-to-speech - TTS capabilities: amd: rocm-neutts default: cpu-neutts nvidia: cuda12-neutts nvidia-cuda-12: cuda12-neutts uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-neutts mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-neutts - name: rocm-neutts license: apache-2.0 description: | NeuTTS Air is the world’s first super-realistic, on-device, TTS speech language model with instant voice cloning. Built off a 0.5B LLM backbone, NeuTTS Air brings natural-sounding speech, real-time performance, built-in security and speaker cloning to your local device - unlocking a new category of embedded voice agents, assistants, toys, and compliance-safe apps. urls: - https://github.com/neuphonic/neutts-air tags: - text-to-speech - TTS capabilities: amd: rocm-neutts default: cpu-neutts nvidia: cuda12-neutts nvidia-cuda-12: cuda12-neutts uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-neutts mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-neutts - name: cpu-neutts-development license: apache-2.0 description: | NeuTTS Air is the world’s first super-realistic, on-device, TTS speech language model with instant voice cloning. Built off a 0.5B LLM backbone, NeuTTS Air brings natural-sounding speech, real-time performance, built-in security and speaker cloning to your local device - unlocking a new category of embedded voice agents, assistants, toys, and compliance-safe apps. urls: - https://github.com/neuphonic/neutts-air tags: - text-to-speech - TTS capabilities: amd: rocm-neutts default: cpu-neutts nvidia: cuda12-neutts nvidia-cuda-12: cuda12-neutts uri: quay.io/go-skynet/local-ai-backends:master-cpu-neutts mirrors: - localai/localai-backends:master-cpu-neutts - name: cuda12-neutts-development license: apache-2.0 description: | NeuTTS Air is the world’s first super-realistic, on-device, TTS speech language model with instant voice cloning. Built off a 0.5B LLM backbone, NeuTTS Air brings natural-sounding speech, real-time performance, built-in security and speaker cloning to your local device - unlocking a new category of embedded voice agents, assistants, toys, and compliance-safe apps. urls: - https://github.com/neuphonic/neutts-air tags: - text-to-speech - TTS capabilities: amd: rocm-neutts default: cpu-neutts nvidia: cuda12-neutts nvidia-cuda-12: cuda12-neutts uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-neutts mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-neutts - name: rocm-neutts-development license: apache-2.0 description: | NeuTTS Air is the world’s first super-realistic, on-device, TTS speech language model with instant voice cloning. Built off a 0.5B LLM backbone, NeuTTS Air brings natural-sounding speech, real-time performance, built-in security and speaker cloning to your local device - unlocking a new category of embedded voice agents, assistants, toys, and compliance-safe apps. urls: - https://github.com/neuphonic/neutts-air tags: - text-to-speech - TTS capabilities: amd: rocm-neutts default: cpu-neutts nvidia: cuda12-neutts nvidia-cuda-12: cuda12-neutts uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-neutts mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-neutts - name: metal-mlx license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run LLMs with MLX urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX capabilities: default: cpu-mlx metal: metal-mlx nvidia: cuda12-mlx nvidia-cuda-12: cuda12-mlx nvidia-cuda-13: cuda13-mlx nvidia-l4t: nvidia-l4t-mlx nvidia-l4t-cuda-12: nvidia-l4t-mlx nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-mlx mirrors: - localai/localai-backends:latest-metal-darwin-arm64-mlx - name: metal-mlx-video license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Generate videos with LTX-2 and converted Wan2.1/Wan2.2 checkpoints using MLX on Apple Silicon. urls: - https://github.com/Blaizzy/mlx-video tags: - text-to-video - image-to-video - MLX capabilities: metal: metal-mlx-video uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-mlx-video mirrors: - localai/localai-backends:latest-metal-darwin-arm64-mlx-video - name: metal-mlx-video-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Generate videos with LTX-2 and converted Wan2.1/Wan2.2 checkpoints using MLX on Apple Silicon. urls: - https://github.com/Blaizzy/mlx-video tags: - text-to-video - image-to-video - MLX capabilities: metal: metal-mlx-video uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-mlx-video mirrors: - localai/localai-backends:master-metal-darwin-arm64-mlx-video - name: mlx-video-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Generate videos with LTX-2 and converted Wan2.1/Wan2.2 checkpoints using MLX on Apple Silicon. urls: - https://github.com/Blaizzy/mlx-video tags: - text-to-video - image-to-video - MLX capabilities: metal: metal-mlx-video-development - name: metal-mlx-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run LLMs with MLX urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX capabilities: default: cpu-mlx metal: metal-mlx nvidia: cuda12-mlx nvidia-cuda-12: cuda12-mlx nvidia-cuda-13: cuda13-mlx nvidia-l4t: nvidia-l4t-mlx nvidia-l4t-cuda-12: nvidia-l4t-mlx nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-mlx mirrors: - localai/localai-backends:master-metal-darwin-arm64-mlx - name: mlx-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run LLMs with MLX urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX capabilities: default: cpu-mlx-development metal: metal-mlx-development nvidia: cuda12-mlx-development nvidia-cuda-12: cuda12-mlx-development nvidia-cuda-13: cuda13-mlx-development nvidia-l4t: nvidia-l4t-mlx-development nvidia-l4t-cuda-12: nvidia-l4t-mlx-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-development - name: metal-mlx-vlm license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Vision-Language Models with MLX urls: - https://github.com/Blaizzy/mlx-vlm tags: - text-to-text - multimodal - vision-language - LLM - MLX capabilities: default: cpu-mlx-vlm metal: metal-mlx-vlm nvidia: cuda12-mlx-vlm nvidia-cuda-12: cuda12-mlx-vlm nvidia-cuda-13: cuda13-mlx-vlm nvidia-l4t: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-mlx-vlm mirrors: - localai/localai-backends:latest-metal-darwin-arm64-mlx-vlm - name: metal-mlx-vlm-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Vision-Language Models with MLX urls: - https://github.com/Blaizzy/mlx-vlm tags: - text-to-text - multimodal - vision-language - LLM - MLX capabilities: default: cpu-mlx-vlm metal: metal-mlx-vlm nvidia: cuda12-mlx-vlm nvidia-cuda-12: cuda12-mlx-vlm nvidia-cuda-13: cuda13-mlx-vlm nvidia-l4t: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-mlx-vlm mirrors: - localai/localai-backends:master-metal-darwin-arm64-mlx-vlm - name: mlx-vlm-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Vision-Language Models with MLX urls: - https://github.com/Blaizzy/mlx-vlm tags: - text-to-text - multimodal - vision-language - LLM - MLX capabilities: default: cpu-mlx-vlm-development metal: metal-mlx-vlm-development nvidia: cuda12-mlx-vlm-development nvidia-cuda-12: cuda12-mlx-vlm-development nvidia-cuda-13: cuda13-mlx-vlm-development nvidia-l4t: nvidia-l4t-mlx-vlm-development nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm-development - name: metal-mlx-audio license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Audio Models with MLX urls: - https://github.com/Blaizzy/mlx-audio tags: - audio-to-text - audio-generation - text-to-audio - LLM - MLX capabilities: default: cpu-mlx-audio metal: metal-mlx-audio nvidia: cuda12-mlx-audio nvidia-cuda-12: cuda12-mlx-audio nvidia-cuda-13: cuda13-mlx-audio nvidia-l4t: nvidia-l4t-mlx-audio nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-mlx-audio mirrors: - localai/localai-backends:latest-metal-darwin-arm64-mlx-audio - name: metal-mlx-audio-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Audio Models with MLX urls: - https://github.com/Blaizzy/mlx-audio tags: - audio-to-text - audio-generation - text-to-audio - LLM - MLX capabilities: default: cpu-mlx-audio metal: metal-mlx-audio nvidia: cuda12-mlx-audio nvidia-cuda-12: cuda12-mlx-audio nvidia-cuda-13: cuda13-mlx-audio nvidia-l4t: nvidia-l4t-mlx-audio nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-mlx-audio mirrors: - localai/localai-backends:master-metal-darwin-arm64-mlx-audio - name: mlx-audio-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Audio Models with MLX urls: - https://github.com/Blaizzy/mlx-audio tags: - audio-to-text - audio-generation - text-to-audio - LLM - MLX capabilities: default: cpu-mlx-audio-development metal: metal-mlx-audio-development nvidia: cuda12-mlx-audio-development nvidia-cuda-12: cuda12-mlx-audio-development nvidia-cuda-13: cuda13-mlx-audio-development nvidia-l4t: nvidia-l4t-mlx-audio-development nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio-development - name: metal-mlx-distributed license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run distributed LLM inference with MLX across multiple Apple Silicon Macs urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX - distributed capabilities: default: cpu-mlx-distributed metal: metal-mlx-distributed nvidia: cuda12-mlx-distributed nvidia-cuda-12: cuda12-mlx-distributed nvidia-cuda-13: cuda13-mlx-distributed nvidia-l4t: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-mlx-distributed mirrors: - localai/localai-backends:latest-metal-darwin-arm64-mlx-distributed - name: metal-mlx-distributed-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run distributed LLM inference with MLX across multiple Apple Silicon Macs urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX - distributed capabilities: default: cpu-mlx-distributed metal: metal-mlx-distributed nvidia: cuda12-mlx-distributed nvidia-cuda-12: cuda12-mlx-distributed nvidia-cuda-13: cuda13-mlx-distributed nvidia-l4t: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-mlx-distributed mirrors: - localai/localai-backends:master-metal-darwin-arm64-mlx-distributed - name: mlx-distributed-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run distributed LLM inference with MLX across multiple Apple Silicon Macs urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX - distributed capabilities: default: cpu-mlx-distributed-development metal: metal-mlx-distributed-development nvidia: cuda12-mlx-distributed-development nvidia-cuda-12: cuda12-mlx-distributed-development nvidia-cuda-13: cuda13-mlx-distributed-development nvidia-l4t: nvidia-l4t-mlx-distributed-development nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed-development - name: cpu-mlx license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run LLMs with MLX urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX capabilities: default: cpu-mlx metal: metal-mlx nvidia: cuda12-mlx nvidia-cuda-12: cuda12-mlx nvidia-cuda-13: cuda13-mlx nvidia-l4t: nvidia-l4t-mlx nvidia-l4t-cuda-12: nvidia-l4t-mlx nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx uri: quay.io/go-skynet/local-ai-backends:latest-cpu-mlx mirrors: - localai/localai-backends:latest-cpu-mlx - name: cpu-mlx-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run LLMs with MLX urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX capabilities: default: cpu-mlx metal: metal-mlx nvidia: cuda12-mlx nvidia-cuda-12: cuda12-mlx nvidia-cuda-13: cuda13-mlx nvidia-l4t: nvidia-l4t-mlx nvidia-l4t-cuda-12: nvidia-l4t-mlx nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx uri: quay.io/go-skynet/local-ai-backends:master-cpu-mlx mirrors: - localai/localai-backends:master-cpu-mlx - name: cuda12-mlx license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run LLMs with MLX urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX capabilities: default: cpu-mlx metal: metal-mlx nvidia: cuda12-mlx nvidia-cuda-12: cuda12-mlx nvidia-cuda-13: cuda13-mlx nvidia-l4t: nvidia-l4t-mlx nvidia-l4t-cuda-12: nvidia-l4t-mlx nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-mlx mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-mlx - name: cuda12-mlx-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run LLMs with MLX urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX capabilities: default: cpu-mlx metal: metal-mlx nvidia: cuda12-mlx nvidia-cuda-12: cuda12-mlx nvidia-cuda-13: cuda13-mlx nvidia-l4t: nvidia-l4t-mlx nvidia-l4t-cuda-12: nvidia-l4t-mlx nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-mlx mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-mlx - name: cuda13-mlx license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run LLMs with MLX urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX capabilities: default: cpu-mlx metal: metal-mlx nvidia: cuda12-mlx nvidia-cuda-12: cuda12-mlx nvidia-cuda-13: cuda13-mlx nvidia-l4t: nvidia-l4t-mlx nvidia-l4t-cuda-12: nvidia-l4t-mlx nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-mlx mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-mlx - name: cuda13-mlx-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run LLMs with MLX urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX capabilities: default: cpu-mlx metal: metal-mlx nvidia: cuda12-mlx nvidia-cuda-12: cuda12-mlx nvidia-cuda-13: cuda13-mlx nvidia-l4t: nvidia-l4t-mlx nvidia-l4t-cuda-12: nvidia-l4t-mlx nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-mlx mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-mlx - name: nvidia-l4t-mlx license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run LLMs with MLX urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX capabilities: default: cpu-mlx metal: metal-mlx nvidia: cuda12-mlx nvidia-cuda-12: cuda12-mlx nvidia-cuda-13: cuda13-mlx nvidia-l4t: nvidia-l4t-mlx nvidia-l4t-cuda-12: nvidia-l4t-mlx nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-mlx mirrors: - localai/localai-backends:latest-nvidia-l4t-mlx - name: nvidia-l4t-mlx-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run LLMs with MLX urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX capabilities: default: cpu-mlx metal: metal-mlx nvidia: cuda12-mlx nvidia-cuda-12: cuda12-mlx nvidia-cuda-13: cuda13-mlx nvidia-l4t: nvidia-l4t-mlx nvidia-l4t-cuda-12: nvidia-l4t-mlx nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-mlx mirrors: - localai/localai-backends:master-nvidia-l4t-mlx - name: cuda13-nvidia-l4t-arm64-mlx license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run LLMs with MLX urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX capabilities: default: cpu-mlx metal: metal-mlx nvidia: cuda12-mlx nvidia-cuda-12: cuda12-mlx nvidia-cuda-13: cuda13-mlx nvidia-l4t: nvidia-l4t-mlx nvidia-l4t-cuda-12: nvidia-l4t-mlx nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx - name: cuda13-nvidia-l4t-arm64-mlx-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run LLMs with MLX urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX capabilities: default: cpu-mlx metal: metal-mlx nvidia: cuda12-mlx nvidia-cuda-12: cuda12-mlx nvidia-cuda-13: cuda13-mlx nvidia-l4t: nvidia-l4t-mlx nvidia-l4t-cuda-12: nvidia-l4t-mlx nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-mlx mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-mlx - name: cpu-mlx-vlm license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Vision-Language Models with MLX urls: - https://github.com/Blaizzy/mlx-vlm tags: - text-to-text - multimodal - vision-language - LLM - MLX capabilities: default: cpu-mlx-vlm metal: metal-mlx-vlm nvidia: cuda12-mlx-vlm nvidia-cuda-12: cuda12-mlx-vlm nvidia-cuda-13: cuda13-mlx-vlm nvidia-l4t: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm uri: quay.io/go-skynet/local-ai-backends:latest-cpu-mlx-vlm mirrors: - localai/localai-backends:latest-cpu-mlx-vlm - name: cpu-mlx-vlm-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Vision-Language Models with MLX urls: - https://github.com/Blaizzy/mlx-vlm tags: - text-to-text - multimodal - vision-language - LLM - MLX capabilities: default: cpu-mlx-vlm metal: metal-mlx-vlm nvidia: cuda12-mlx-vlm nvidia-cuda-12: cuda12-mlx-vlm nvidia-cuda-13: cuda13-mlx-vlm nvidia-l4t: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm uri: quay.io/go-skynet/local-ai-backends:master-cpu-mlx-vlm mirrors: - localai/localai-backends:master-cpu-mlx-vlm - name: cuda12-mlx-vlm license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Vision-Language Models with MLX urls: - https://github.com/Blaizzy/mlx-vlm tags: - text-to-text - multimodal - vision-language - LLM - MLX capabilities: default: cpu-mlx-vlm metal: metal-mlx-vlm nvidia: cuda12-mlx-vlm nvidia-cuda-12: cuda12-mlx-vlm nvidia-cuda-13: cuda13-mlx-vlm nvidia-l4t: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-mlx-vlm mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-mlx-vlm - name: cuda12-mlx-vlm-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Vision-Language Models with MLX urls: - https://github.com/Blaizzy/mlx-vlm tags: - text-to-text - multimodal - vision-language - LLM - MLX capabilities: default: cpu-mlx-vlm metal: metal-mlx-vlm nvidia: cuda12-mlx-vlm nvidia-cuda-12: cuda12-mlx-vlm nvidia-cuda-13: cuda13-mlx-vlm nvidia-l4t: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-mlx-vlm mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-mlx-vlm - name: cuda13-mlx-vlm license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Vision-Language Models with MLX urls: - https://github.com/Blaizzy/mlx-vlm tags: - text-to-text - multimodal - vision-language - LLM - MLX capabilities: default: cpu-mlx-vlm metal: metal-mlx-vlm nvidia: cuda12-mlx-vlm nvidia-cuda-12: cuda12-mlx-vlm nvidia-cuda-13: cuda13-mlx-vlm nvidia-l4t: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-mlx-vlm mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-mlx-vlm - name: cuda13-mlx-vlm-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Vision-Language Models with MLX urls: - https://github.com/Blaizzy/mlx-vlm tags: - text-to-text - multimodal - vision-language - LLM - MLX capabilities: default: cpu-mlx-vlm metal: metal-mlx-vlm nvidia: cuda12-mlx-vlm nvidia-cuda-12: cuda12-mlx-vlm nvidia-cuda-13: cuda13-mlx-vlm nvidia-l4t: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-mlx-vlm mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-mlx-vlm - name: nvidia-l4t-mlx-vlm license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Vision-Language Models with MLX urls: - https://github.com/Blaizzy/mlx-vlm tags: - text-to-text - multimodal - vision-language - LLM - MLX capabilities: default: cpu-mlx-vlm metal: metal-mlx-vlm nvidia: cuda12-mlx-vlm nvidia-cuda-12: cuda12-mlx-vlm nvidia-cuda-13: cuda13-mlx-vlm nvidia-l4t: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-mlx-vlm mirrors: - localai/localai-backends:latest-nvidia-l4t-mlx-vlm - name: nvidia-l4t-mlx-vlm-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Vision-Language Models with MLX urls: - https://github.com/Blaizzy/mlx-vlm tags: - text-to-text - multimodal - vision-language - LLM - MLX capabilities: default: cpu-mlx-vlm metal: metal-mlx-vlm nvidia: cuda12-mlx-vlm nvidia-cuda-12: cuda12-mlx-vlm nvidia-cuda-13: cuda13-mlx-vlm nvidia-l4t: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-mlx-vlm mirrors: - localai/localai-backends:master-nvidia-l4t-mlx-vlm - name: cuda13-nvidia-l4t-arm64-mlx-vlm license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Vision-Language Models with MLX urls: - https://github.com/Blaizzy/mlx-vlm tags: - text-to-text - multimodal - vision-language - LLM - MLX capabilities: default: cpu-mlx-vlm metal: metal-mlx-vlm nvidia: cuda12-mlx-vlm nvidia-cuda-12: cuda12-mlx-vlm nvidia-cuda-13: cuda13-mlx-vlm nvidia-l4t: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx-vlm mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx-vlm - name: cuda13-nvidia-l4t-arm64-mlx-vlm-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Vision-Language Models with MLX urls: - https://github.com/Blaizzy/mlx-vlm tags: - text-to-text - multimodal - vision-language - LLM - MLX capabilities: default: cpu-mlx-vlm metal: metal-mlx-vlm nvidia: cuda12-mlx-vlm nvidia-cuda-12: cuda12-mlx-vlm nvidia-cuda-13: cuda13-mlx-vlm nvidia-l4t: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-12: nvidia-l4t-mlx-vlm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-vlm uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-mlx-vlm mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-mlx-vlm - name: cpu-mlx-audio license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Audio Models with MLX urls: - https://github.com/Blaizzy/mlx-audio tags: - audio-to-text - audio-generation - text-to-audio - LLM - MLX capabilities: default: cpu-mlx-audio metal: metal-mlx-audio nvidia: cuda12-mlx-audio nvidia-cuda-12: cuda12-mlx-audio nvidia-cuda-13: cuda13-mlx-audio nvidia-l4t: nvidia-l4t-mlx-audio nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio uri: quay.io/go-skynet/local-ai-backends:latest-cpu-mlx-audio mirrors: - localai/localai-backends:latest-cpu-mlx-audio - name: cpu-mlx-audio-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Audio Models with MLX urls: - https://github.com/Blaizzy/mlx-audio tags: - audio-to-text - audio-generation - text-to-audio - LLM - MLX capabilities: default: cpu-mlx-audio metal: metal-mlx-audio nvidia: cuda12-mlx-audio nvidia-cuda-12: cuda12-mlx-audio nvidia-cuda-13: cuda13-mlx-audio nvidia-l4t: nvidia-l4t-mlx-audio nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio uri: quay.io/go-skynet/local-ai-backends:master-cpu-mlx-audio mirrors: - localai/localai-backends:master-cpu-mlx-audio - name: cuda12-mlx-audio license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Audio Models with MLX urls: - https://github.com/Blaizzy/mlx-audio tags: - audio-to-text - audio-generation - text-to-audio - LLM - MLX capabilities: default: cpu-mlx-audio metal: metal-mlx-audio nvidia: cuda12-mlx-audio nvidia-cuda-12: cuda12-mlx-audio nvidia-cuda-13: cuda13-mlx-audio nvidia-l4t: nvidia-l4t-mlx-audio nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-mlx-audio mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-mlx-audio - name: cuda12-mlx-audio-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Audio Models with MLX urls: - https://github.com/Blaizzy/mlx-audio tags: - audio-to-text - audio-generation - text-to-audio - LLM - MLX capabilities: default: cpu-mlx-audio metal: metal-mlx-audio nvidia: cuda12-mlx-audio nvidia-cuda-12: cuda12-mlx-audio nvidia-cuda-13: cuda13-mlx-audio nvidia-l4t: nvidia-l4t-mlx-audio nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-mlx-audio mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-mlx-audio - name: cuda13-mlx-audio license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Audio Models with MLX urls: - https://github.com/Blaizzy/mlx-audio tags: - audio-to-text - audio-generation - text-to-audio - LLM - MLX capabilities: default: cpu-mlx-audio metal: metal-mlx-audio nvidia: cuda12-mlx-audio nvidia-cuda-12: cuda12-mlx-audio nvidia-cuda-13: cuda13-mlx-audio nvidia-l4t: nvidia-l4t-mlx-audio nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-mlx-audio mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-mlx-audio - name: cuda13-mlx-audio-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Audio Models with MLX urls: - https://github.com/Blaizzy/mlx-audio tags: - audio-to-text - audio-generation - text-to-audio - LLM - MLX capabilities: default: cpu-mlx-audio metal: metal-mlx-audio nvidia: cuda12-mlx-audio nvidia-cuda-12: cuda12-mlx-audio nvidia-cuda-13: cuda13-mlx-audio nvidia-l4t: nvidia-l4t-mlx-audio nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-mlx-audio mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-mlx-audio - name: nvidia-l4t-mlx-audio license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Audio Models with MLX urls: - https://github.com/Blaizzy/mlx-audio tags: - audio-to-text - audio-generation - text-to-audio - LLM - MLX capabilities: default: cpu-mlx-audio metal: metal-mlx-audio nvidia: cuda12-mlx-audio nvidia-cuda-12: cuda12-mlx-audio nvidia-cuda-13: cuda13-mlx-audio nvidia-l4t: nvidia-l4t-mlx-audio nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-mlx-audio mirrors: - localai/localai-backends:latest-nvidia-l4t-mlx-audio - name: nvidia-l4t-mlx-audio-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Audio Models with MLX urls: - https://github.com/Blaizzy/mlx-audio tags: - audio-to-text - audio-generation - text-to-audio - LLM - MLX capabilities: default: cpu-mlx-audio metal: metal-mlx-audio nvidia: cuda12-mlx-audio nvidia-cuda-12: cuda12-mlx-audio nvidia-cuda-13: cuda13-mlx-audio nvidia-l4t: nvidia-l4t-mlx-audio nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-mlx-audio mirrors: - localai/localai-backends:master-nvidia-l4t-mlx-audio - name: cuda13-nvidia-l4t-arm64-mlx-audio license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Audio Models with MLX urls: - https://github.com/Blaizzy/mlx-audio tags: - audio-to-text - audio-generation - text-to-audio - LLM - MLX capabilities: default: cpu-mlx-audio metal: metal-mlx-audio nvidia: cuda12-mlx-audio nvidia-cuda-12: cuda12-mlx-audio nvidia-cuda-13: cuda13-mlx-audio nvidia-l4t: nvidia-l4t-mlx-audio nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx-audio mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx-audio - name: cuda13-nvidia-l4t-arm64-mlx-audio-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run Audio Models with MLX urls: - https://github.com/Blaizzy/mlx-audio tags: - audio-to-text - audio-generation - text-to-audio - LLM - MLX capabilities: default: cpu-mlx-audio metal: metal-mlx-audio nvidia: cuda12-mlx-audio nvidia-cuda-12: cuda12-mlx-audio nvidia-cuda-13: cuda13-mlx-audio nvidia-l4t: nvidia-l4t-mlx-audio nvidia-l4t-cuda-12: nvidia-l4t-mlx-audio nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-audio uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-mlx-audio mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-mlx-audio - name: cpu-mlx-distributed license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run distributed LLM inference with MLX across multiple Apple Silicon Macs urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX - distributed capabilities: default: cpu-mlx-distributed metal: metal-mlx-distributed nvidia: cuda12-mlx-distributed nvidia-cuda-12: cuda12-mlx-distributed nvidia-cuda-13: cuda13-mlx-distributed nvidia-l4t: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed uri: quay.io/go-skynet/local-ai-backends:latest-cpu-mlx-distributed mirrors: - localai/localai-backends:latest-cpu-mlx-distributed - name: cpu-mlx-distributed-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run distributed LLM inference with MLX across multiple Apple Silicon Macs urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX - distributed capabilities: default: cpu-mlx-distributed metal: metal-mlx-distributed nvidia: cuda12-mlx-distributed nvidia-cuda-12: cuda12-mlx-distributed nvidia-cuda-13: cuda13-mlx-distributed nvidia-l4t: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed uri: quay.io/go-skynet/local-ai-backends:master-cpu-mlx-distributed mirrors: - localai/localai-backends:master-cpu-mlx-distributed - name: cuda12-mlx-distributed license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run distributed LLM inference with MLX across multiple Apple Silicon Macs urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX - distributed capabilities: default: cpu-mlx-distributed metal: metal-mlx-distributed nvidia: cuda12-mlx-distributed nvidia-cuda-12: cuda12-mlx-distributed nvidia-cuda-13: cuda13-mlx-distributed nvidia-l4t: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-mlx-distributed mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-mlx-distributed - name: cuda12-mlx-distributed-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run distributed LLM inference with MLX across multiple Apple Silicon Macs urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX - distributed capabilities: default: cpu-mlx-distributed metal: metal-mlx-distributed nvidia: cuda12-mlx-distributed nvidia-cuda-12: cuda12-mlx-distributed nvidia-cuda-13: cuda13-mlx-distributed nvidia-l4t: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-mlx-distributed mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-mlx-distributed - name: cuda13-mlx-distributed license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run distributed LLM inference with MLX across multiple Apple Silicon Macs urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX - distributed capabilities: default: cpu-mlx-distributed metal: metal-mlx-distributed nvidia: cuda12-mlx-distributed nvidia-cuda-12: cuda12-mlx-distributed nvidia-cuda-13: cuda13-mlx-distributed nvidia-l4t: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-mlx-distributed mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-mlx-distributed - name: cuda13-mlx-distributed-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run distributed LLM inference with MLX across multiple Apple Silicon Macs urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX - distributed capabilities: default: cpu-mlx-distributed metal: metal-mlx-distributed nvidia: cuda12-mlx-distributed nvidia-cuda-12: cuda12-mlx-distributed nvidia-cuda-13: cuda13-mlx-distributed nvidia-l4t: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-mlx-distributed mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-mlx-distributed - name: nvidia-l4t-mlx-distributed license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run distributed LLM inference with MLX across multiple Apple Silicon Macs urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX - distributed capabilities: default: cpu-mlx-distributed metal: metal-mlx-distributed nvidia: cuda12-mlx-distributed nvidia-cuda-12: cuda12-mlx-distributed nvidia-cuda-13: cuda13-mlx-distributed nvidia-l4t: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-mlx-distributed mirrors: - localai/localai-backends:latest-nvidia-l4t-mlx-distributed - name: nvidia-l4t-mlx-distributed-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run distributed LLM inference with MLX across multiple Apple Silicon Macs urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX - distributed capabilities: default: cpu-mlx-distributed metal: metal-mlx-distributed nvidia: cuda12-mlx-distributed nvidia-cuda-12: cuda12-mlx-distributed nvidia-cuda-13: cuda13-mlx-distributed nvidia-l4t: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-mlx-distributed mirrors: - localai/localai-backends:master-nvidia-l4t-mlx-distributed - name: cuda13-nvidia-l4t-arm64-mlx-distributed license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run distributed LLM inference with MLX across multiple Apple Silicon Macs urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX - distributed capabilities: default: cpu-mlx-distributed metal: metal-mlx-distributed nvidia: cuda12-mlx-distributed nvidia-cuda-12: cuda12-mlx-distributed nvidia-cuda-13: cuda13-mlx-distributed nvidia-l4t: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx-distributed mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-mlx-distributed - name: cuda13-nvidia-l4t-arm64-mlx-distributed-development license: MIT icon: https://avatars.githubusercontent.com/u/102832242?s=200&v=4 description: | Run distributed LLM inference with MLX across multiple Apple Silicon Macs urls: - https://github.com/ml-explore/mlx-lm tags: - text-to-text - LLM - MLX - distributed capabilities: default: cpu-mlx-distributed metal: metal-mlx-distributed nvidia: cuda12-mlx-distributed nvidia-cuda-12: cuda12-mlx-distributed nvidia-cuda-13: cuda13-mlx-distributed nvidia-l4t: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-12: nvidia-l4t-mlx-distributed nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-mlx-distributed uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-mlx-distributed mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-mlx-distributed - name: cpu-kitten-tts license: apache-2.0 description: | Kitten TTS is a text-to-speech model that can generate speech from text. urls: - https://github.com/KittenML/KittenTTS tags: - text-to-speech - TTS capabilities: default: cpu-kitten-tts metal: metal-kitten-tts uri: quay.io/go-skynet/local-ai-backends:latest-kitten-tts mirrors: - localai/localai-backends:latest-kitten-tts - name: cpu-kitten-tts-development license: apache-2.0 description: | Kitten TTS is a text-to-speech model that can generate speech from text. urls: - https://github.com/KittenML/KittenTTS tags: - text-to-speech - TTS capabilities: default: cpu-kitten-tts metal: metal-kitten-tts uri: quay.io/go-skynet/local-ai-backends:master-kitten-tts mirrors: - localai/localai-backends:master-kitten-tts - name: kitten-tts-development license: apache-2.0 description: | Kitten TTS is a text-to-speech model that can generate speech from text. urls: - https://github.com/KittenML/KittenTTS tags: - text-to-speech - TTS capabilities: default: cpu-kitten-tts-development metal: metal-kitten-tts-development - name: metal-kitten-tts license: apache-2.0 description: | Kitten TTS is a text-to-speech model that can generate speech from text. urls: - https://github.com/KittenML/KittenTTS tags: - text-to-speech - TTS capabilities: default: cpu-kitten-tts metal: metal-kitten-tts uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-kitten-tts mirrors: - localai/localai-backends:latest-metal-darwin-arm64-kitten-tts - name: metal-kitten-tts-development license: apache-2.0 description: | Kitten TTS is a text-to-speech model that can generate speech from text. urls: - https://github.com/KittenML/KittenTTS tags: - text-to-speech - TTS capabilities: default: cpu-kitten-tts metal: metal-kitten-tts uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-kitten-tts mirrors: - localai/localai-backends:master-metal-darwin-arm64-kitten-tts - name: cpu-local-store alias: local-store license: MIT description: | Local Store is a local-first, self-hosted, and open-source vector database. urls: - https://github.com/mudler/LocalAI tags: - vector-database - local-first - open-source - CPU capabilities: default: cpu-local-store metal: metal-local-store uri: quay.io/go-skynet/local-ai-backends:latest-cpu-local-store mirrors: - localai/localai-backends:latest-cpu-local-store - name: cpu-local-store-development alias: local-store license: MIT description: | Local Store is a local-first, self-hosted, and open-source vector database. urls: - https://github.com/mudler/LocalAI tags: - vector-database - local-first - open-source - CPU capabilities: default: cpu-local-store metal: metal-local-store uri: quay.io/go-skynet/local-ai-backends:master-cpu-local-store mirrors: - localai/localai-backends:master-cpu-local-store - name: local-store-development alias: local-store license: MIT description: | Local Store is a local-first, self-hosted, and open-source vector database. urls: - https://github.com/mudler/LocalAI tags: - vector-database - local-first - open-source - CPU capabilities: default: cpu-local-store-development metal: metal-local-store-development - name: metal-local-store license: MIT description: | Local Store is a local-first, self-hosted, and open-source vector database. urls: - https://github.com/mudler/LocalAI tags: - vector-database - local-first - open-source - CPU capabilities: default: cpu-local-store metal: metal-local-store uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-local-store mirrors: - localai/localai-backends:latest-metal-darwin-arm64-local-store - name: metal-local-store-development alias: local-store license: MIT description: | Local Store is a local-first, self-hosted, and open-source vector database. urls: - https://github.com/mudler/LocalAI tags: - vector-database - local-first - open-source - CPU capabilities: default: cpu-local-store metal: metal-local-store uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-local-store mirrors: - localai/localai-backends:master-metal-darwin-arm64-local-store - name: cpu-cloud-proxy alias: cloud-proxy license: MIT description: | Forward OpenAI-compatible and Anthropic chat requests to external providers. urls: - https://github.com/mudler/LocalAI/tree/master/backend/go/cloud-proxy tags: - text-to-text - cloud - proxy - CPU capabilities: default: cpu-cloud-proxy metal: metal-cloud-proxy uri: quay.io/go-skynet/local-ai-backends:latest-cpu-cloud-proxy mirrors: - localai/localai-backends:latest-cpu-cloud-proxy - name: cpu-cloud-proxy-development alias: cloud-proxy license: MIT description: | Forward OpenAI-compatible and Anthropic chat requests to external providers. urls: - https://github.com/mudler/LocalAI/tree/master/backend/go/cloud-proxy tags: - text-to-text - cloud - proxy - CPU capabilities: default: cpu-cloud-proxy metal: metal-cloud-proxy uri: quay.io/go-skynet/local-ai-backends:master-cpu-cloud-proxy mirrors: - localai/localai-backends:master-cpu-cloud-proxy - name: cloud-proxy-development alias: cloud-proxy license: MIT description: | Forward OpenAI-compatible and Anthropic chat requests to external providers. urls: - https://github.com/mudler/LocalAI/tree/master/backend/go/cloud-proxy tags: - text-to-text - cloud - proxy - CPU capabilities: default: cpu-cloud-proxy-development metal: metal-cloud-proxy-development - name: metal-cloud-proxy alias: cloud-proxy license: MIT description: | Forward OpenAI-compatible and Anthropic chat requests to external providers. urls: - https://github.com/mudler/LocalAI/tree/master/backend/go/cloud-proxy tags: - text-to-text - cloud - proxy - CPU capabilities: default: cpu-cloud-proxy metal: metal-cloud-proxy uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-cloud-proxy mirrors: - localai/localai-backends:latest-metal-darwin-arm64-cloud-proxy - name: metal-cloud-proxy-development alias: cloud-proxy license: MIT description: | Forward OpenAI-compatible and Anthropic chat requests to external providers. urls: - https://github.com/mudler/LocalAI/tree/master/backend/go/cloud-proxy tags: - text-to-text - cloud - proxy - CPU capabilities: default: cpu-cloud-proxy metal: metal-cloud-proxy uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-cloud-proxy mirrors: - localai/localai-backends:master-metal-darwin-arm64-cloud-proxy - name: cpu-localai-proxy alias: localai-proxy license: MIT description: | Serve a model from another LocalAI instance: text, embeddings, rerank, audio, image and video requests are forwarded to its REST API. urls: - https://github.com/mudler/LocalAI/tree/master/backend/go/localai-proxy tags: - text-to-text - proxy - CPU capabilities: default: cpu-localai-proxy metal: metal-localai-proxy uri: quay.io/go-skynet/local-ai-backends:latest-cpu-localai-proxy mirrors: - localai/localai-backends:latest-cpu-localai-proxy - name: cpu-localai-proxy-development alias: localai-proxy license: MIT description: | Serve a model from another LocalAI instance: text, embeddings, rerank, audio, image and video requests are forwarded to its REST API. urls: - https://github.com/mudler/LocalAI/tree/master/backend/go/localai-proxy tags: - text-to-text - proxy - CPU capabilities: default: cpu-localai-proxy metal: metal-localai-proxy uri: quay.io/go-skynet/local-ai-backends:master-cpu-localai-proxy mirrors: - localai/localai-backends:master-cpu-localai-proxy - name: localai-proxy-development alias: localai-proxy license: MIT description: | Serve a model from another LocalAI instance: text, embeddings, rerank, audio, image and video requests are forwarded to its REST API. urls: - https://github.com/mudler/LocalAI/tree/master/backend/go/localai-proxy tags: - text-to-text - proxy - CPU capabilities: default: cpu-localai-proxy-development metal: metal-localai-proxy-development - name: metal-localai-proxy alias: localai-proxy license: MIT description: | Serve a model from another LocalAI instance: text, embeddings, rerank, audio, image and video requests are forwarded to its REST API. urls: - https://github.com/mudler/LocalAI/tree/master/backend/go/localai-proxy tags: - text-to-text - proxy - CPU capabilities: default: cpu-localai-proxy metal: metal-localai-proxy uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-localai-proxy mirrors: - localai/localai-backends:latest-metal-darwin-arm64-localai-proxy - name: metal-localai-proxy-development alias: localai-proxy license: MIT description: | Serve a model from another LocalAI instance: text, embeddings, rerank, audio, image and video requests are forwarded to its REST API. urls: - https://github.com/mudler/LocalAI/tree/master/backend/go/localai-proxy tags: - text-to-text - proxy - CPU capabilities: default: cpu-localai-proxy metal: metal-localai-proxy uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-localai-proxy mirrors: - localai/localai-backends:master-metal-darwin-arm64-localai-proxy - name: cpu-valkey-store alias: valkey-store license: MIT description: | Valkey Store is a Valkey Search (FT.*) backed vector store for LocalAI. It persists vectors across restarts and supports opt-in HNSW indexing. Requires a reachable Valkey Search server (valkey/valkey-bundle). urls: - https://github.com/mudler/LocalAI tags: - vector-database - valkey - open-source - CPU capabilities: default: cpu-valkey-store metal: metal-valkey-store uri: quay.io/go-skynet/local-ai-backends:latest-cpu-valkey-store mirrors: - localai/localai-backends:latest-cpu-valkey-store - name: cpu-valkey-store-development alias: valkey-store license: MIT description: | Valkey Store is a Valkey Search (FT.*) backed vector store for LocalAI. It persists vectors across restarts and supports opt-in HNSW indexing. Requires a reachable Valkey Search server (valkey/valkey-bundle). urls: - https://github.com/mudler/LocalAI tags: - vector-database - valkey - open-source - CPU capabilities: default: cpu-valkey-store metal: metal-valkey-store uri: quay.io/go-skynet/local-ai-backends:master-cpu-valkey-store mirrors: - localai/localai-backends:master-cpu-valkey-store - name: valkey-store-development alias: valkey-store license: MIT description: | Valkey Store is a Valkey Search (FT.*) backed vector store for LocalAI. It persists vectors across restarts and supports opt-in HNSW indexing. Requires a reachable Valkey Search server (valkey/valkey-bundle). urls: - https://github.com/mudler/LocalAI tags: - vector-database - valkey - open-source - CPU capabilities: default: cpu-valkey-store-development metal: metal-valkey-store-development - name: metal-valkey-store license: MIT description: | Valkey Store is a Valkey Search (FT.*) backed vector store for LocalAI. It persists vectors across restarts and supports opt-in HNSW indexing. Requires a reachable Valkey Search server (valkey/valkey-bundle). urls: - https://github.com/mudler/LocalAI tags: - vector-database - valkey - open-source - CPU capabilities: default: cpu-valkey-store metal: metal-valkey-store uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-valkey-store mirrors: - localai/localai-backends:latest-metal-darwin-arm64-valkey-store - name: metal-valkey-store-development alias: valkey-store license: MIT description: | Valkey Store is a Valkey Search (FT.*) backed vector store for LocalAI. It persists vectors across restarts and supports opt-in HNSW indexing. Requires a reachable Valkey Search server (valkey/valkey-bundle). urls: - https://github.com/mudler/LocalAI tags: - vector-database - valkey - open-source - CPU capabilities: default: cpu-valkey-store metal: metal-valkey-store uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-valkey-store mirrors: - localai/localai-backends:master-metal-darwin-arm64-valkey-store - name: cpu-qdrant-store alias: qdrant-store license: MIT description: | Qdrant Store is a Qdrant-backed vector store for LocalAI. It persists vectors across restarts in HNSW-indexed collections and works with self-hosted Qdrant (single node or cluster) and Qdrant Cloud. Requires a reachable Qdrant server (gRPC port, 6334 by default). urls: - https://github.com/mudler/LocalAI - https://github.com/qdrant/qdrant tags: - vector-database - qdrant - open-source - CPU capabilities: default: cpu-qdrant-store metal: metal-qdrant-store uri: quay.io/go-skynet/local-ai-backends:latest-cpu-qdrant-store mirrors: - localai/localai-backends:latest-cpu-qdrant-store - name: cpu-qdrant-store-development alias: qdrant-store license: MIT description: | Qdrant Store is a Qdrant-backed vector store for LocalAI. It persists vectors across restarts in HNSW-indexed collections and works with self-hosted Qdrant (single node or cluster) and Qdrant Cloud. Requires a reachable Qdrant server (gRPC port, 6334 by default). urls: - https://github.com/mudler/LocalAI - https://github.com/qdrant/qdrant tags: - vector-database - qdrant - open-source - CPU capabilities: default: cpu-qdrant-store metal: metal-qdrant-store uri: quay.io/go-skynet/local-ai-backends:master-cpu-qdrant-store mirrors: - localai/localai-backends:master-cpu-qdrant-store - name: qdrant-store-development alias: qdrant-store license: MIT description: | Qdrant Store is a Qdrant-backed vector store for LocalAI. It persists vectors across restarts in HNSW-indexed collections and works with self-hosted Qdrant (single node or cluster) and Qdrant Cloud. Requires a reachable Qdrant server (gRPC port, 6334 by default). urls: - https://github.com/mudler/LocalAI - https://github.com/qdrant/qdrant tags: - vector-database - qdrant - open-source - CPU capabilities: default: cpu-qdrant-store-development metal: metal-qdrant-store-development - name: metal-qdrant-store license: MIT description: | Qdrant Store is a Qdrant-backed vector store for LocalAI. It persists vectors across restarts in HNSW-indexed collections and works with self-hosted Qdrant (single node or cluster) and Qdrant Cloud. Requires a reachable Qdrant server (gRPC port, 6334 by default). urls: - https://github.com/mudler/LocalAI - https://github.com/qdrant/qdrant tags: - vector-database - qdrant - open-source - CPU capabilities: default: cpu-qdrant-store metal: metal-qdrant-store uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-qdrant-store mirrors: - localai/localai-backends:latest-metal-darwin-arm64-qdrant-store - name: metal-qdrant-store-development alias: qdrant-store license: MIT description: | Qdrant Store is a Qdrant-backed vector store for LocalAI. It persists vectors across restarts in HNSW-indexed collections and works with self-hosted Qdrant (single node or cluster) and Qdrant Cloud. Requires a reachable Qdrant server (gRPC port, 6334 by default). urls: - https://github.com/mudler/LocalAI - https://github.com/qdrant/qdrant tags: - vector-database - qdrant - open-source - CPU capabilities: default: cpu-qdrant-store metal: metal-qdrant-store uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-qdrant-store mirrors: - localai/localai-backends:master-metal-darwin-arm64-qdrant-store - name: cpu-opus alias: opus license: BSD-3-Clause description: | Opus audio codec backend for encoding and decoding audio. Required for WebRTC transport in the Realtime API. urls: - https://opus-codec.org/ tags: - audio-codec - opus - WebRTC - realtime capabilities: default: cpu-opus metal: metal-opus uri: quay.io/go-skynet/local-ai-backends:latest-cpu-opus mirrors: - localai/localai-backends:latest-cpu-opus - name: cpu-opus-development alias: opus license: BSD-3-Clause description: | Opus audio codec backend for encoding and decoding audio. Required for WebRTC transport in the Realtime API. urls: - https://opus-codec.org/ tags: - audio-codec - opus - WebRTC - realtime capabilities: default: cpu-opus metal: metal-opus uri: quay.io/go-skynet/local-ai-backends:master-cpu-opus mirrors: - localai/localai-backends:master-cpu-opus - name: metal-opus alias: opus license: BSD-3-Clause description: | Opus audio codec backend for encoding and decoding audio. Required for WebRTC transport in the Realtime API. urls: - https://opus-codec.org/ tags: - audio-codec - opus - WebRTC - realtime capabilities: default: cpu-opus metal: metal-opus uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-opus mirrors: - localai/localai-backends:latest-metal-darwin-arm64-opus - name: metal-opus-development alias: opus license: BSD-3-Clause description: | Opus audio codec backend for encoding and decoding audio. Required for WebRTC transport in the Realtime API. urls: - https://opus-codec.org/ tags: - audio-codec - opus - WebRTC - realtime capabilities: default: cpu-opus metal: metal-opus uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-opus mirrors: - localai/localai-backends:master-metal-darwin-arm64-opus - name: cpu-silero-vad icon: https://user-images.githubusercontent.com/12515440/89997349-b3523080-dc94-11ea-9906-ca2e8bc50535.png description: | Silero VAD: pre-trained enterprise-grade Voice Activity Detector. Silero VAD is a voice activity detection model that can be used to detect whether a given audio contains speech or not. urls: - https://github.com/snakers4/silero-vad tags: - voice-activity-detection - VAD - silero-vad - CPU capabilities: default: cpu-silero-vad metal: metal-silero-vad uri: quay.io/go-skynet/local-ai-backends:latest-cpu-silero-vad mirrors: - localai/localai-backends:latest-cpu-silero-vad - name: cpu-silero-vad-development icon: https://user-images.githubusercontent.com/12515440/89997349-b3523080-dc94-11ea-9906-ca2e8bc50535.png description: | Silero VAD: pre-trained enterprise-grade Voice Activity Detector. Silero VAD is a voice activity detection model that can be used to detect whether a given audio contains speech or not. urls: - https://github.com/snakers4/silero-vad tags: - voice-activity-detection - VAD - silero-vad - CPU capabilities: default: cpu-silero-vad metal: metal-silero-vad uri: quay.io/go-skynet/local-ai-backends:master-cpu-silero-vad mirrors: - localai/localai-backends:master-cpu-silero-vad - name: silero-vad-development icon: https://user-images.githubusercontent.com/12515440/89997349-b3523080-dc94-11ea-9906-ca2e8bc50535.png description: | Silero VAD: pre-trained enterprise-grade Voice Activity Detector. Silero VAD is a voice activity detection model that can be used to detect whether a given audio contains speech or not. urls: - https://github.com/snakers4/silero-vad tags: - voice-activity-detection - VAD - silero-vad - CPU capabilities: default: cpu-silero-vad-development metal: metal-silero-vad-development - name: metal-silero-vad icon: https://user-images.githubusercontent.com/12515440/89997349-b3523080-dc94-11ea-9906-ca2e8bc50535.png description: | Silero VAD: pre-trained enterprise-grade Voice Activity Detector. Silero VAD is a voice activity detection model that can be used to detect whether a given audio contains speech or not. urls: - https://github.com/snakers4/silero-vad tags: - voice-activity-detection - VAD - silero-vad - CPU capabilities: default: cpu-silero-vad metal: metal-silero-vad uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-silero-vad mirrors: - localai/localai-backends:latest-metal-darwin-arm64-silero-vad - name: metal-silero-vad-development icon: https://user-images.githubusercontent.com/12515440/89997349-b3523080-dc94-11ea-9906-ca2e8bc50535.png description: | Silero VAD: pre-trained enterprise-grade Voice Activity Detector. Silero VAD is a voice activity detection model that can be used to detect whether a given audio contains speech or not. urls: - https://github.com/snakers4/silero-vad tags: - voice-activity-detection - VAD - silero-vad - CPU capabilities: default: cpu-silero-vad metal: metal-silero-vad uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-silero-vad mirrors: - localai/localai-backends:master-metal-darwin-arm64-silero-vad - name: cpu-piper license: MIT icon: https://github.com/OHF-Voice/piper1-gpl/raw/main/etc/logo.png description: | A fast, local neural text to speech system urls: - https://github.com/rhasspy/piper - https://github.com/mudler/go-piper tags: - text-to-speech - TTS capabilities: default: cpu-piper metal: metal-piper uri: quay.io/go-skynet/local-ai-backends:latest-piper mirrors: - localai/localai-backends:latest-piper - name: cpu-piper-development license: MIT icon: https://github.com/OHF-Voice/piper1-gpl/raw/main/etc/logo.png description: | A fast, local neural text to speech system urls: - https://github.com/rhasspy/piper - https://github.com/mudler/go-piper tags: - text-to-speech - TTS capabilities: default: cpu-piper metal: metal-piper uri: quay.io/go-skynet/local-ai-backends:master-piper mirrors: - localai/localai-backends:master-piper - name: piper-development license: MIT icon: https://github.com/OHF-Voice/piper1-gpl/raw/main/etc/logo.png description: | A fast, local neural text to speech system urls: - https://github.com/rhasspy/piper - https://github.com/mudler/go-piper tags: - text-to-speech - TTS capabilities: default: cpu-piper-development metal: metal-piper-development - name: metal-piper license: MIT icon: https://github.com/OHF-Voice/piper1-gpl/raw/main/etc/logo.png description: | A fast, local neural text to speech system urls: - https://github.com/rhasspy/piper - https://github.com/mudler/go-piper tags: - text-to-speech - TTS capabilities: default: cpu-piper metal: metal-piper uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-piper mirrors: - localai/localai-backends:latest-metal-darwin-arm64-piper - name: metal-piper-development license: MIT icon: https://github.com/OHF-Voice/piper1-gpl/raw/main/etc/logo.png description: | A fast, local neural text to speech system urls: - https://github.com/rhasspy/piper - https://github.com/mudler/go-piper tags: - text-to-speech - TTS capabilities: default: cpu-piper metal: metal-piper uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-piper mirrors: - localai/localai-backends:master-metal-darwin-arm64-piper - name: nvidia-l4t-arm64-llama-cpp alias: llama-cpp license: mit icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png description: | LLM inference in C/C++ urls: - https://github.com/ggerganov/llama.cpp tags: - text-to-text - text-to-speech - TTS - LLM - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-llama-cpp default: cpu-llama-cpp intel: intel-sycl-f16-llama-cpp metal: metal-llama-cpp nvidia: cuda12-llama-cpp nvidia-cuda-12: cuda12-llama-cpp nvidia-cuda-13: cuda13-llama-cpp nvidia-l4t: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp vulkan: vulkan-llama-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-llama-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-arm64-llama-cpp - name: nvidia-l4t-arm64-llama-cpp-development alias: llama-cpp license: mit icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png description: | LLM inference in C/C++ urls: - https://github.com/ggerganov/llama.cpp tags: - text-to-text - text-to-speech - TTS - LLM - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-llama-cpp default: cpu-llama-cpp intel: intel-sycl-f16-llama-cpp metal: metal-llama-cpp nvidia: cuda12-llama-cpp nvidia-cuda-12: cuda12-llama-cpp nvidia-cuda-13: cuda13-llama-cpp nvidia-l4t: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp vulkan: vulkan-llama-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-llama-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-arm64-llama-cpp - name: cuda13-nvidia-l4t-arm64-llama-cpp alias: llama-cpp license: mit icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png description: | LLM inference in C/C++ urls: - https://github.com/ggerganov/llama.cpp tags: - text-to-text - text-to-speech - TTS - LLM - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-llama-cpp default: cpu-llama-cpp intel: intel-sycl-f16-llama-cpp metal: metal-llama-cpp nvidia: cuda12-llama-cpp nvidia-cuda-12: cuda12-llama-cpp nvidia-cuda-13: cuda13-llama-cpp nvidia-l4t: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp vulkan: vulkan-llama-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-llama-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-llama-cpp - name: cuda13-nvidia-l4t-arm64-llama-cpp-development alias: llama-cpp license: mit icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png description: | LLM inference in C/C++ urls: - https://github.com/ggerganov/llama.cpp tags: - text-to-text - text-to-speech - TTS - LLM - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-llama-cpp default: cpu-llama-cpp intel: intel-sycl-f16-llama-cpp metal: metal-llama-cpp nvidia: cuda12-llama-cpp nvidia-cuda-12: cuda12-llama-cpp nvidia-cuda-13: cuda13-llama-cpp nvidia-l4t: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp vulkan: vulkan-llama-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-llama-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-llama-cpp - name: cpu-llama-cpp alias: llama-cpp license: mit icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png description: | LLM inference in C/C++ urls: - https://github.com/ggerganov/llama.cpp tags: - text-to-text - text-to-speech - TTS - LLM - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-llama-cpp default: cpu-llama-cpp intel: intel-sycl-f16-llama-cpp metal: metal-llama-cpp nvidia: cuda12-llama-cpp nvidia-cuda-12: cuda12-llama-cpp nvidia-cuda-13: cuda13-llama-cpp nvidia-l4t: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp vulkan: vulkan-llama-cpp uri: quay.io/go-skynet/local-ai-backends:latest-cpu-llama-cpp mirrors: - localai/localai-backends:latest-cpu-llama-cpp - name: cpu-llama-cpp-development alias: llama-cpp license: mit icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png description: | LLM inference in C/C++ urls: - https://github.com/ggerganov/llama.cpp tags: - text-to-text - text-to-speech - TTS - LLM - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-llama-cpp default: cpu-llama-cpp intel: intel-sycl-f16-llama-cpp metal: metal-llama-cpp nvidia: cuda12-llama-cpp nvidia-cuda-12: cuda12-llama-cpp nvidia-cuda-13: cuda13-llama-cpp nvidia-l4t: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp vulkan: vulkan-llama-cpp uri: quay.io/go-skynet/local-ai-backends:master-cpu-llama-cpp mirrors: - localai/localai-backends:master-cpu-llama-cpp - name: cuda12-llama-cpp alias: llama-cpp license: mit icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png description: | LLM inference in C/C++ urls: - https://github.com/ggerganov/llama.cpp tags: - text-to-text - text-to-speech - TTS - LLM - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-llama-cpp default: cpu-llama-cpp intel: intel-sycl-f16-llama-cpp metal: metal-llama-cpp nvidia: cuda12-llama-cpp nvidia-cuda-12: cuda12-llama-cpp nvidia-cuda-13: cuda13-llama-cpp nvidia-l4t: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp vulkan: vulkan-llama-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-llama-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-llama-cpp - name: rocm-llama-cpp alias: llama-cpp license: mit icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png description: | LLM inference in C/C++ urls: - https://github.com/ggerganov/llama.cpp tags: - text-to-text - text-to-speech - TTS - LLM - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-llama-cpp default: cpu-llama-cpp intel: intel-sycl-f16-llama-cpp metal: metal-llama-cpp nvidia: cuda12-llama-cpp nvidia-cuda-12: cuda12-llama-cpp nvidia-cuda-13: cuda13-llama-cpp nvidia-l4t: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp vulkan: vulkan-llama-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-llama-cpp mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-llama-cpp - name: intel-sycl-f32-llama-cpp alias: llama-cpp license: mit icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png description: | LLM inference in C/C++ urls: - https://github.com/ggerganov/llama.cpp tags: - text-to-text - text-to-speech - TTS - LLM - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-llama-cpp default: cpu-llama-cpp intel: intel-sycl-f16-llama-cpp metal: metal-llama-cpp nvidia: cuda12-llama-cpp nvidia-cuda-12: cuda12-llama-cpp nvidia-cuda-13: cuda13-llama-cpp nvidia-l4t: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp vulkan: vulkan-llama-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-llama-cpp mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f32-llama-cpp - name: intel-sycl-f16-llama-cpp alias: llama-cpp license: mit icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png description: | LLM inference in C/C++ urls: - https://github.com/ggerganov/llama.cpp tags: - text-to-text - text-to-speech - TTS - LLM - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-llama-cpp default: cpu-llama-cpp intel: intel-sycl-f16-llama-cpp metal: metal-llama-cpp nvidia: cuda12-llama-cpp nvidia-cuda-12: cuda12-llama-cpp nvidia-cuda-13: cuda13-llama-cpp nvidia-l4t: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp vulkan: vulkan-llama-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-llama-cpp mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f16-llama-cpp - name: vulkan-llama-cpp alias: llama-cpp license: mit icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png description: | LLM inference in C/C++ urls: - https://github.com/ggerganov/llama.cpp tags: - text-to-text - text-to-speech - TTS - LLM - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-llama-cpp default: cpu-llama-cpp intel: intel-sycl-f16-llama-cpp metal: metal-llama-cpp nvidia: cuda12-llama-cpp nvidia-cuda-12: cuda12-llama-cpp nvidia-cuda-13: cuda13-llama-cpp nvidia-l4t: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp vulkan: vulkan-llama-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-llama-cpp mirrors: - localai/localai-backends:latest-gpu-vulkan-llama-cpp - name: vulkan-llama-cpp-development alias: llama-cpp license: mit icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png description: | LLM inference in C/C++ urls: - https://github.com/ggerganov/llama.cpp tags: - text-to-text - text-to-speech - TTS - LLM - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-llama-cpp default: cpu-llama-cpp intel: intel-sycl-f16-llama-cpp metal: metal-llama-cpp nvidia: cuda12-llama-cpp nvidia-cuda-12: cuda12-llama-cpp nvidia-cuda-13: cuda13-llama-cpp nvidia-l4t: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp vulkan: vulkan-llama-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-llama-cpp mirrors: - localai/localai-backends:master-gpu-vulkan-llama-cpp - name: metal-llama-cpp alias: llama-cpp license: mit icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png description: | LLM inference in C/C++ urls: - https://github.com/ggerganov/llama.cpp tags: - text-to-text - text-to-speech - TTS - LLM - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-llama-cpp default: cpu-llama-cpp intel: intel-sycl-f16-llama-cpp metal: metal-llama-cpp nvidia: cuda12-llama-cpp nvidia-cuda-12: cuda12-llama-cpp nvidia-cuda-13: cuda13-llama-cpp nvidia-l4t: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp vulkan: vulkan-llama-cpp uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-llama-cpp mirrors: - localai/localai-backends:latest-metal-darwin-arm64-llama-cpp - name: metal-llama-cpp-development alias: llama-cpp license: mit icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png description: | LLM inference in C/C++ urls: - https://github.com/ggerganov/llama.cpp tags: - text-to-text - text-to-speech - TTS - LLM - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-llama-cpp default: cpu-llama-cpp intel: intel-sycl-f16-llama-cpp metal: metal-llama-cpp nvidia: cuda12-llama-cpp nvidia-cuda-12: cuda12-llama-cpp nvidia-cuda-13: cuda13-llama-cpp nvidia-l4t: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp vulkan: vulkan-llama-cpp uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-llama-cpp mirrors: - localai/localai-backends:master-metal-darwin-arm64-llama-cpp - name: cuda12-llama-cpp-development alias: llama-cpp license: mit icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png description: | LLM inference in C/C++ urls: - https://github.com/ggerganov/llama.cpp tags: - text-to-text - text-to-speech - TTS - LLM - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-llama-cpp default: cpu-llama-cpp intel: intel-sycl-f16-llama-cpp metal: metal-llama-cpp nvidia: cuda12-llama-cpp nvidia-cuda-12: cuda12-llama-cpp nvidia-cuda-13: cuda13-llama-cpp nvidia-l4t: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp vulkan: vulkan-llama-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-llama-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-llama-cpp - name: rocm-llama-cpp-development alias: llama-cpp license: mit icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png description: | LLM inference in C/C++ urls: - https://github.com/ggerganov/llama.cpp tags: - text-to-text - text-to-speech - TTS - LLM - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-llama-cpp default: cpu-llama-cpp intel: intel-sycl-f16-llama-cpp metal: metal-llama-cpp nvidia: cuda12-llama-cpp nvidia-cuda-12: cuda12-llama-cpp nvidia-cuda-13: cuda13-llama-cpp nvidia-l4t: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp vulkan: vulkan-llama-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-llama-cpp mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-llama-cpp - name: intel-sycl-f32-llama-cpp-development alias: llama-cpp license: mit icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png description: | LLM inference in C/C++ urls: - https://github.com/ggerganov/llama.cpp tags: - text-to-text - text-to-speech - TTS - LLM - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-llama-cpp default: cpu-llama-cpp intel: intel-sycl-f16-llama-cpp metal: metal-llama-cpp nvidia: cuda12-llama-cpp nvidia-cuda-12: cuda12-llama-cpp nvidia-cuda-13: cuda13-llama-cpp nvidia-l4t: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp vulkan: vulkan-llama-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-llama-cpp mirrors: - localai/localai-backends:master-gpu-intel-sycl-f32-llama-cpp - name: intel-sycl-f16-llama-cpp-development alias: llama-cpp license: mit icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png description: | LLM inference in C/C++ urls: - https://github.com/ggerganov/llama.cpp tags: - text-to-text - text-to-speech - TTS - LLM - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-llama-cpp default: cpu-llama-cpp intel: intel-sycl-f16-llama-cpp metal: metal-llama-cpp nvidia: cuda12-llama-cpp nvidia-cuda-12: cuda12-llama-cpp nvidia-cuda-13: cuda13-llama-cpp nvidia-l4t: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp vulkan: vulkan-llama-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-llama-cpp mirrors: - localai/localai-backends:master-gpu-intel-sycl-f16-llama-cpp - name: cuda13-llama-cpp alias: llama-cpp license: mit icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png description: | LLM inference in C/C++ urls: - https://github.com/ggerganov/llama.cpp tags: - text-to-text - text-to-speech - TTS - LLM - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-llama-cpp default: cpu-llama-cpp intel: intel-sycl-f16-llama-cpp metal: metal-llama-cpp nvidia: cuda12-llama-cpp nvidia-cuda-12: cuda12-llama-cpp nvidia-cuda-13: cuda13-llama-cpp nvidia-l4t: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp vulkan: vulkan-llama-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-llama-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-llama-cpp - name: cuda13-llama-cpp-development alias: llama-cpp license: mit icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png description: | LLM inference in C/C++ urls: - https://github.com/ggerganov/llama.cpp tags: - text-to-text - text-to-speech - TTS - LLM - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-llama-cpp default: cpu-llama-cpp intel: intel-sycl-f16-llama-cpp metal: metal-llama-cpp nvidia: cuda12-llama-cpp nvidia-cuda-12: cuda12-llama-cpp nvidia-cuda-13: cuda13-llama-cpp nvidia-l4t: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-llama-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-llama-cpp vulkan: vulkan-llama-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-llama-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-llama-cpp - name: cpu-ik-llama-cpp alias: ik-llama-cpp license: mit description: | Fork of llama.cpp optimized for CPU performance by ikawrakow urls: - https://github.com/ikawrakow/ik_llama.cpp tags: - text-to-text - LLM - CPU capabilities: default: cpu-ik-llama-cpp uri: quay.io/go-skynet/local-ai-backends:latest-cpu-ik-llama-cpp mirrors: - localai/localai-backends:latest-cpu-ik-llama-cpp - name: cpu-ik-llama-cpp-development alias: ik-llama-cpp license: mit description: | Fork of llama.cpp optimized for CPU performance by ikawrakow urls: - https://github.com/ikawrakow/ik_llama.cpp tags: - text-to-text - LLM - CPU capabilities: default: cpu-ik-llama-cpp uri: quay.io/go-skynet/local-ai-backends:master-cpu-ik-llama-cpp mirrors: - localai/localai-backends:master-cpu-ik-llama-cpp - name: cpu-turboquant alias: turboquant license: mit description: | Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama. urls: - https://github.com/TheTom/llama-cpp-turboquant tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - turboquant - kv-cache capabilities: amd: rocm-turboquant default: cpu-turboquant intel: intel-sycl-f16-turboquant nvidia: cuda12-turboquant nvidia-cuda-12: cuda12-turboquant nvidia-cuda-13: cuda13-turboquant nvidia-l4t: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant vulkan: vulkan-turboquant uri: quay.io/go-skynet/local-ai-backends:latest-cpu-turboquant mirrors: - localai/localai-backends:latest-cpu-turboquant - name: cpu-turboquant-development alias: turboquant license: mit description: | Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama. urls: - https://github.com/TheTom/llama-cpp-turboquant tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - turboquant - kv-cache capabilities: amd: rocm-turboquant default: cpu-turboquant intel: intel-sycl-f16-turboquant nvidia: cuda12-turboquant nvidia-cuda-12: cuda12-turboquant nvidia-cuda-13: cuda13-turboquant nvidia-l4t: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant vulkan: vulkan-turboquant uri: quay.io/go-skynet/local-ai-backends:master-cpu-turboquant mirrors: - localai/localai-backends:master-cpu-turboquant - name: cuda12-turboquant alias: turboquant license: mit description: | Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama. urls: - https://github.com/TheTom/llama-cpp-turboquant tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - turboquant - kv-cache capabilities: amd: rocm-turboquant default: cpu-turboquant intel: intel-sycl-f16-turboquant nvidia: cuda12-turboquant nvidia-cuda-12: cuda12-turboquant nvidia-cuda-13: cuda13-turboquant nvidia-l4t: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant vulkan: vulkan-turboquant uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-turboquant mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-turboquant - name: cuda12-turboquant-development alias: turboquant license: mit description: | Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama. urls: - https://github.com/TheTom/llama-cpp-turboquant tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - turboquant - kv-cache capabilities: amd: rocm-turboquant default: cpu-turboquant intel: intel-sycl-f16-turboquant nvidia: cuda12-turboquant nvidia-cuda-12: cuda12-turboquant nvidia-cuda-13: cuda13-turboquant nvidia-l4t: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant vulkan: vulkan-turboquant uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-turboquant mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-turboquant - name: cuda13-turboquant alias: turboquant license: mit description: | Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama. urls: - https://github.com/TheTom/llama-cpp-turboquant tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - turboquant - kv-cache capabilities: amd: rocm-turboquant default: cpu-turboquant intel: intel-sycl-f16-turboquant nvidia: cuda12-turboquant nvidia-cuda-12: cuda12-turboquant nvidia-cuda-13: cuda13-turboquant nvidia-l4t: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant vulkan: vulkan-turboquant uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-turboquant mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-turboquant - name: cuda13-turboquant-development alias: turboquant license: mit description: | Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama. urls: - https://github.com/TheTom/llama-cpp-turboquant tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - turboquant - kv-cache capabilities: amd: rocm-turboquant default: cpu-turboquant intel: intel-sycl-f16-turboquant nvidia: cuda12-turboquant nvidia-cuda-12: cuda12-turboquant nvidia-cuda-13: cuda13-turboquant nvidia-l4t: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant vulkan: vulkan-turboquant uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-turboquant mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-turboquant - name: rocm-turboquant alias: turboquant license: mit description: | Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama. urls: - https://github.com/TheTom/llama-cpp-turboquant tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - turboquant - kv-cache capabilities: amd: rocm-turboquant default: cpu-turboquant intel: intel-sycl-f16-turboquant nvidia: cuda12-turboquant nvidia-cuda-12: cuda12-turboquant nvidia-cuda-13: cuda13-turboquant nvidia-l4t: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant vulkan: vulkan-turboquant uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-turboquant mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-turboquant - name: rocm-turboquant-development alias: turboquant license: mit description: | Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama. urls: - https://github.com/TheTom/llama-cpp-turboquant tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - turboquant - kv-cache capabilities: amd: rocm-turboquant default: cpu-turboquant intel: intel-sycl-f16-turboquant nvidia: cuda12-turboquant nvidia-cuda-12: cuda12-turboquant nvidia-cuda-13: cuda13-turboquant nvidia-l4t: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant vulkan: vulkan-turboquant uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-turboquant mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-turboquant - name: intel-sycl-f32-turboquant alias: turboquant license: mit description: | Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama. urls: - https://github.com/TheTom/llama-cpp-turboquant tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - turboquant - kv-cache capabilities: amd: rocm-turboquant default: cpu-turboquant intel: intel-sycl-f16-turboquant nvidia: cuda12-turboquant nvidia-cuda-12: cuda12-turboquant nvidia-cuda-13: cuda13-turboquant nvidia-l4t: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant vulkan: vulkan-turboquant uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-turboquant mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f32-turboquant - name: intel-sycl-f32-turboquant-development alias: turboquant license: mit description: | Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama. urls: - https://github.com/TheTom/llama-cpp-turboquant tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - turboquant - kv-cache capabilities: amd: rocm-turboquant default: cpu-turboquant intel: intel-sycl-f16-turboquant nvidia: cuda12-turboquant nvidia-cuda-12: cuda12-turboquant nvidia-cuda-13: cuda13-turboquant nvidia-l4t: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant vulkan: vulkan-turboquant uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-turboquant mirrors: - localai/localai-backends:master-gpu-intel-sycl-f32-turboquant - name: intel-sycl-f16-turboquant alias: turboquant license: mit description: | Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama. urls: - https://github.com/TheTom/llama-cpp-turboquant tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - turboquant - kv-cache capabilities: amd: rocm-turboquant default: cpu-turboquant intel: intel-sycl-f16-turboquant nvidia: cuda12-turboquant nvidia-cuda-12: cuda12-turboquant nvidia-cuda-13: cuda13-turboquant nvidia-l4t: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant vulkan: vulkan-turboquant uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-turboquant mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f16-turboquant - name: intel-sycl-f16-turboquant-development alias: turboquant license: mit description: | Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama. urls: - https://github.com/TheTom/llama-cpp-turboquant tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - turboquant - kv-cache capabilities: amd: rocm-turboquant default: cpu-turboquant intel: intel-sycl-f16-turboquant nvidia: cuda12-turboquant nvidia-cuda-12: cuda12-turboquant nvidia-cuda-13: cuda13-turboquant nvidia-l4t: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant vulkan: vulkan-turboquant uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-turboquant mirrors: - localai/localai-backends:master-gpu-intel-sycl-f16-turboquant - name: vulkan-turboquant alias: turboquant license: mit description: | Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama. urls: - https://github.com/TheTom/llama-cpp-turboquant tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - turboquant - kv-cache capabilities: amd: rocm-turboquant default: cpu-turboquant intel: intel-sycl-f16-turboquant nvidia: cuda12-turboquant nvidia-cuda-12: cuda12-turboquant nvidia-cuda-13: cuda13-turboquant nvidia-l4t: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant vulkan: vulkan-turboquant uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-turboquant mirrors: - localai/localai-backends:latest-gpu-vulkan-turboquant - name: vulkan-turboquant-development alias: turboquant license: mit description: | Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama. urls: - https://github.com/TheTom/llama-cpp-turboquant tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - turboquant - kv-cache capabilities: amd: rocm-turboquant default: cpu-turboquant intel: intel-sycl-f16-turboquant nvidia: cuda12-turboquant nvidia-cuda-12: cuda12-turboquant nvidia-cuda-13: cuda13-turboquant nvidia-l4t: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant vulkan: vulkan-turboquant uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-turboquant mirrors: - localai/localai-backends:master-gpu-vulkan-turboquant - name: nvidia-l4t-arm64-turboquant alias: turboquant license: mit description: | Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama. urls: - https://github.com/TheTom/llama-cpp-turboquant tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - turboquant - kv-cache capabilities: amd: rocm-turboquant default: cpu-turboquant intel: intel-sycl-f16-turboquant nvidia: cuda12-turboquant nvidia-cuda-12: cuda12-turboquant nvidia-cuda-13: cuda13-turboquant nvidia-l4t: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant vulkan: vulkan-turboquant uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-turboquant mirrors: - localai/localai-backends:latest-nvidia-l4t-arm64-turboquant - name: nvidia-l4t-arm64-turboquant-development alias: turboquant license: mit description: | Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama. urls: - https://github.com/TheTom/llama-cpp-turboquant tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - turboquant - kv-cache capabilities: amd: rocm-turboquant default: cpu-turboquant intel: intel-sycl-f16-turboquant nvidia: cuda12-turboquant nvidia-cuda-12: cuda12-turboquant nvidia-cuda-13: cuda13-turboquant nvidia-l4t: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant vulkan: vulkan-turboquant uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-turboquant mirrors: - localai/localai-backends:master-nvidia-l4t-arm64-turboquant - name: cuda13-nvidia-l4t-arm64-turboquant alias: turboquant license: mit description: | Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama. urls: - https://github.com/TheTom/llama-cpp-turboquant tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - turboquant - kv-cache capabilities: amd: rocm-turboquant default: cpu-turboquant intel: intel-sycl-f16-turboquant nvidia: cuda12-turboquant nvidia-cuda-12: cuda12-turboquant nvidia-cuda-13: cuda13-turboquant nvidia-l4t: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant vulkan: vulkan-turboquant uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-turboquant mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-turboquant - name: cuda13-nvidia-l4t-arm64-turboquant-development alias: turboquant license: mit description: | Fork of llama.cpp adding the TurboQuant KV-cache quantization scheme. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama. urls: - https://github.com/TheTom/llama-cpp-turboquant tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - turboquant - kv-cache capabilities: amd: rocm-turboquant default: cpu-turboquant intel: intel-sycl-f16-turboquant nvidia: cuda12-turboquant nvidia-cuda-12: cuda12-turboquant nvidia-cuda-13: cuda13-turboquant nvidia-l4t: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-12: nvidia-l4t-arm64-turboquant nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-turboquant vulkan: vulkan-turboquant uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-turboquant mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-turboquant - name: cpu-bonsai alias: bonsai license: apache-2.0 description: | Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit) weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp backend. urls: - https://github.com/PrismML-Eng/llama.cpp - https://huggingface.co/prism-ml tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - bonsai - 1-bit - ternary capabilities: amd: rocm-bonsai default: cpu-bonsai intel: intel-sycl-f16-bonsai nvidia: cuda12-bonsai nvidia-cuda-12: cuda12-bonsai nvidia-cuda-13: cuda13-bonsai nvidia-l4t: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai vulkan: vulkan-bonsai uri: quay.io/go-skynet/local-ai-backends:latest-cpu-bonsai mirrors: - localai/localai-backends:latest-cpu-bonsai - name: cpu-bonsai-development alias: bonsai license: apache-2.0 description: | Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit) weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp backend. urls: - https://github.com/PrismML-Eng/llama.cpp - https://huggingface.co/prism-ml tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - bonsai - 1-bit - ternary capabilities: amd: rocm-bonsai default: cpu-bonsai intel: intel-sycl-f16-bonsai nvidia: cuda12-bonsai nvidia-cuda-12: cuda12-bonsai nvidia-cuda-13: cuda13-bonsai nvidia-l4t: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai vulkan: vulkan-bonsai uri: quay.io/go-skynet/local-ai-backends:master-cpu-bonsai mirrors: - localai/localai-backends:master-cpu-bonsai - name: cuda12-bonsai alias: bonsai license: apache-2.0 description: | Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit) weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp backend. urls: - https://github.com/PrismML-Eng/llama.cpp - https://huggingface.co/prism-ml tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - bonsai - 1-bit - ternary capabilities: amd: rocm-bonsai default: cpu-bonsai intel: intel-sycl-f16-bonsai nvidia: cuda12-bonsai nvidia-cuda-12: cuda12-bonsai nvidia-cuda-13: cuda13-bonsai nvidia-l4t: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai vulkan: vulkan-bonsai uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-bonsai mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-bonsai - name: cuda12-bonsai-development alias: bonsai license: apache-2.0 description: | Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit) weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp backend. urls: - https://github.com/PrismML-Eng/llama.cpp - https://huggingface.co/prism-ml tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - bonsai - 1-bit - ternary capabilities: amd: rocm-bonsai default: cpu-bonsai intel: intel-sycl-f16-bonsai nvidia: cuda12-bonsai nvidia-cuda-12: cuda12-bonsai nvidia-cuda-13: cuda13-bonsai nvidia-l4t: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai vulkan: vulkan-bonsai uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-bonsai mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-bonsai - name: cuda13-bonsai alias: bonsai license: apache-2.0 description: | Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit) weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp backend. urls: - https://github.com/PrismML-Eng/llama.cpp - https://huggingface.co/prism-ml tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - bonsai - 1-bit - ternary capabilities: amd: rocm-bonsai default: cpu-bonsai intel: intel-sycl-f16-bonsai nvidia: cuda12-bonsai nvidia-cuda-12: cuda12-bonsai nvidia-cuda-13: cuda13-bonsai nvidia-l4t: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai vulkan: vulkan-bonsai uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-bonsai mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-bonsai - name: cuda13-bonsai-development alias: bonsai license: apache-2.0 description: | Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit) weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp backend. urls: - https://github.com/PrismML-Eng/llama.cpp - https://huggingface.co/prism-ml tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - bonsai - 1-bit - ternary capabilities: amd: rocm-bonsai default: cpu-bonsai intel: intel-sycl-f16-bonsai nvidia: cuda12-bonsai nvidia-cuda-12: cuda12-bonsai nvidia-cuda-13: cuda13-bonsai nvidia-l4t: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai vulkan: vulkan-bonsai uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-bonsai mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-bonsai - name: rocm-bonsai alias: bonsai license: apache-2.0 description: | Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit) weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp backend. urls: - https://github.com/PrismML-Eng/llama.cpp - https://huggingface.co/prism-ml tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - bonsai - 1-bit - ternary capabilities: amd: rocm-bonsai default: cpu-bonsai intel: intel-sycl-f16-bonsai nvidia: cuda12-bonsai nvidia-cuda-12: cuda12-bonsai nvidia-cuda-13: cuda13-bonsai nvidia-l4t: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai vulkan: vulkan-bonsai uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-bonsai mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-bonsai - name: rocm-bonsai-development alias: bonsai license: apache-2.0 description: | Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit) weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp backend. urls: - https://github.com/PrismML-Eng/llama.cpp - https://huggingface.co/prism-ml tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - bonsai - 1-bit - ternary capabilities: amd: rocm-bonsai default: cpu-bonsai intel: intel-sycl-f16-bonsai nvidia: cuda12-bonsai nvidia-cuda-12: cuda12-bonsai nvidia-cuda-13: cuda13-bonsai nvidia-l4t: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai vulkan: vulkan-bonsai uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-bonsai mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-bonsai - name: intel-sycl-f32-bonsai alias: bonsai license: apache-2.0 description: | Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit) weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp backend. urls: - https://github.com/PrismML-Eng/llama.cpp - https://huggingface.co/prism-ml tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - bonsai - 1-bit - ternary capabilities: amd: rocm-bonsai default: cpu-bonsai intel: intel-sycl-f16-bonsai nvidia: cuda12-bonsai nvidia-cuda-12: cuda12-bonsai nvidia-cuda-13: cuda13-bonsai nvidia-l4t: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai vulkan: vulkan-bonsai uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-bonsai mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f32-bonsai - name: intel-sycl-f32-bonsai-development alias: bonsai license: apache-2.0 description: | Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit) weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp backend. urls: - https://github.com/PrismML-Eng/llama.cpp - https://huggingface.co/prism-ml tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - bonsai - 1-bit - ternary capabilities: amd: rocm-bonsai default: cpu-bonsai intel: intel-sycl-f16-bonsai nvidia: cuda12-bonsai nvidia-cuda-12: cuda12-bonsai nvidia-cuda-13: cuda13-bonsai nvidia-l4t: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai vulkan: vulkan-bonsai uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-bonsai mirrors: - localai/localai-backends:master-gpu-intel-sycl-f32-bonsai - name: intel-sycl-f16-bonsai alias: bonsai license: apache-2.0 description: | Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit) weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp backend. urls: - https://github.com/PrismML-Eng/llama.cpp - https://huggingface.co/prism-ml tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - bonsai - 1-bit - ternary capabilities: amd: rocm-bonsai default: cpu-bonsai intel: intel-sycl-f16-bonsai nvidia: cuda12-bonsai nvidia-cuda-12: cuda12-bonsai nvidia-cuda-13: cuda13-bonsai nvidia-l4t: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai vulkan: vulkan-bonsai uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-bonsai mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f16-bonsai - name: intel-sycl-f16-bonsai-development alias: bonsai license: apache-2.0 description: | Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit) weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp backend. urls: - https://github.com/PrismML-Eng/llama.cpp - https://huggingface.co/prism-ml tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - bonsai - 1-bit - ternary capabilities: amd: rocm-bonsai default: cpu-bonsai intel: intel-sycl-f16-bonsai nvidia: cuda12-bonsai nvidia-cuda-12: cuda12-bonsai nvidia-cuda-13: cuda13-bonsai nvidia-l4t: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai vulkan: vulkan-bonsai uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-bonsai mirrors: - localai/localai-backends:master-gpu-intel-sycl-f16-bonsai - name: vulkan-bonsai alias: bonsai license: apache-2.0 description: | Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit) weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp backend. urls: - https://github.com/PrismML-Eng/llama.cpp - https://huggingface.co/prism-ml tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - bonsai - 1-bit - ternary capabilities: amd: rocm-bonsai default: cpu-bonsai intel: intel-sycl-f16-bonsai nvidia: cuda12-bonsai nvidia-cuda-12: cuda12-bonsai nvidia-cuda-13: cuda13-bonsai nvidia-l4t: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai vulkan: vulkan-bonsai uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-bonsai mirrors: - localai/localai-backends:latest-gpu-vulkan-bonsai - name: vulkan-bonsai-development alias: bonsai license: apache-2.0 description: | Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit) weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp backend. urls: - https://github.com/PrismML-Eng/llama.cpp - https://huggingface.co/prism-ml tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - bonsai - 1-bit - ternary capabilities: amd: rocm-bonsai default: cpu-bonsai intel: intel-sycl-f16-bonsai nvidia: cuda12-bonsai nvidia-cuda-12: cuda12-bonsai nvidia-cuda-13: cuda13-bonsai nvidia-l4t: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai vulkan: vulkan-bonsai uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-bonsai mirrors: - localai/localai-backends:master-gpu-vulkan-bonsai - name: nvidia-l4t-arm64-bonsai alias: bonsai license: apache-2.0 description: | Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit) weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp backend. urls: - https://github.com/PrismML-Eng/llama.cpp - https://huggingface.co/prism-ml tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - bonsai - 1-bit - ternary capabilities: amd: rocm-bonsai default: cpu-bonsai intel: intel-sycl-f16-bonsai nvidia: cuda12-bonsai nvidia-cuda-12: cuda12-bonsai nvidia-cuda-13: cuda13-bonsai nvidia-l4t: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai vulkan: vulkan-bonsai uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-bonsai mirrors: - localai/localai-backends:latest-nvidia-l4t-arm64-bonsai - name: nvidia-l4t-arm64-bonsai-development alias: bonsai license: apache-2.0 description: | Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit) weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp backend. urls: - https://github.com/PrismML-Eng/llama.cpp - https://huggingface.co/prism-ml tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - bonsai - 1-bit - ternary capabilities: amd: rocm-bonsai default: cpu-bonsai intel: intel-sycl-f16-bonsai nvidia: cuda12-bonsai nvidia-cuda-12: cuda12-bonsai nvidia-cuda-13: cuda13-bonsai nvidia-l4t: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai vulkan: vulkan-bonsai uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-bonsai mirrors: - localai/localai-backends:master-nvidia-l4t-arm64-bonsai - name: cuda13-nvidia-l4t-arm64-bonsai alias: bonsai license: apache-2.0 description: | Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit) weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp backend. urls: - https://github.com/PrismML-Eng/llama.cpp - https://huggingface.co/prism-ml tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - bonsai - 1-bit - ternary capabilities: amd: rocm-bonsai default: cpu-bonsai intel: intel-sycl-f16-bonsai nvidia: cuda12-bonsai nvidia-cuda-12: cuda12-bonsai nvidia-cuda-13: cuda13-bonsai nvidia-l4t: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai vulkan: vulkan-bonsai uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-bonsai mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-bonsai - name: cuda13-nvidia-l4t-arm64-bonsai-development alias: bonsai license: apache-2.0 description: | Fork of llama.cpp (PrismML) adding the Q1_0 (1-bit) and Q2_0 (ternary, 1.58-bit) weight-quantization kernels used by the Bonsai and Ternary-Bonsai models. Reuses the LocalAI llama.cpp gRPC server sources against the fork's libllama, so it drives these sub-2-bit models with the same OpenAI-compatible API as the stock llama.cpp backend. urls: - https://github.com/PrismML-Eng/llama.cpp - https://huggingface.co/prism-ml tags: - text-to-text - LLM - CPU - GPU - CUDA - HIP - bonsai - 1-bit - ternary capabilities: amd: rocm-bonsai default: cpu-bonsai intel: intel-sycl-f16-bonsai nvidia: cuda12-bonsai nvidia-cuda-12: cuda12-bonsai nvidia-cuda-13: cuda13-bonsai nvidia-l4t: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-12: nvidia-l4t-arm64-bonsai nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-bonsai vulkan: vulkan-bonsai uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-bonsai mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-bonsai - name: cpu-ds4 alias: ds4 license: mit description: | antirez/ds4 - DeepSeek V4 Flash inference engine. Single-model, optimized for Metal (Darwin) and CUDA (Linux). Requires the GGUFs published at huggingface.co/antirez/deepseek-v4-gguf. urls: - https://github.com/antirez/ds4 tags: - text-to-text - LLM - CPU - CUDA - Metal capabilities: default: cpu-ds4 metal: metal-ds4 metal-darwin-arm64: metal-ds4 nvidia: cuda13-ds4 nvidia-cuda-13: cuda13-ds4 nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ds4 uri: quay.io/go-skynet/local-ai-backends:latest-cpu-ds4 mirrors: - localai/localai-backends:latest-cpu-ds4 - name: cpu-ds4-development alias: ds4 license: mit description: | antirez/ds4 - DeepSeek V4 Flash inference engine. Single-model, optimized for Metal (Darwin) and CUDA (Linux). Requires the GGUFs published at huggingface.co/antirez/deepseek-v4-gguf. urls: - https://github.com/antirez/ds4 tags: - text-to-text - LLM - CPU - CUDA - Metal capabilities: default: cpu-ds4 metal: metal-ds4 metal-darwin-arm64: metal-ds4 nvidia: cuda13-ds4 nvidia-cuda-13: cuda13-ds4 nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ds4 uri: quay.io/go-skynet/local-ai-backends:master-cpu-ds4 mirrors: - localai/localai-backends:master-cpu-ds4 - name: cuda13-ds4 alias: ds4 license: mit description: | antirez/ds4 - DeepSeek V4 Flash inference engine. Single-model, optimized for Metal (Darwin) and CUDA (Linux). Requires the GGUFs published at huggingface.co/antirez/deepseek-v4-gguf. urls: - https://github.com/antirez/ds4 tags: - text-to-text - LLM - CPU - CUDA - Metal capabilities: default: cpu-ds4 metal: metal-ds4 metal-darwin-arm64: metal-ds4 nvidia: cuda13-ds4 nvidia-cuda-13: cuda13-ds4 nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ds4 uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-ds4 mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-ds4 - name: cuda13-ds4-development alias: ds4 license: mit description: | antirez/ds4 - DeepSeek V4 Flash inference engine. Single-model, optimized for Metal (Darwin) and CUDA (Linux). Requires the GGUFs published at huggingface.co/antirez/deepseek-v4-gguf. urls: - https://github.com/antirez/ds4 tags: - text-to-text - LLM - CPU - CUDA - Metal capabilities: default: cpu-ds4 metal: metal-ds4 metal-darwin-arm64: metal-ds4 nvidia: cuda13-ds4 nvidia-cuda-13: cuda13-ds4 nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ds4 uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-ds4 mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-ds4 - name: cuda13-nvidia-l4t-arm64-ds4 alias: ds4 license: mit description: | antirez/ds4 - DeepSeek V4 Flash inference engine. Single-model, optimized for Metal (Darwin) and CUDA (Linux). Requires the GGUFs published at huggingface.co/antirez/deepseek-v4-gguf. urls: - https://github.com/antirez/ds4 tags: - text-to-text - LLM - CPU - CUDA - Metal capabilities: default: cpu-ds4 metal: metal-ds4 metal-darwin-arm64: metal-ds4 nvidia: cuda13-ds4 nvidia-cuda-13: cuda13-ds4 nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ds4 uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-ds4 mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-ds4 - name: cuda13-nvidia-l4t-arm64-ds4-development alias: ds4 license: mit description: | antirez/ds4 - DeepSeek V4 Flash inference engine. Single-model, optimized for Metal (Darwin) and CUDA (Linux). Requires the GGUFs published at huggingface.co/antirez/deepseek-v4-gguf. urls: - https://github.com/antirez/ds4 tags: - text-to-text - LLM - CPU - CUDA - Metal capabilities: default: cpu-ds4 metal: metal-ds4 metal-darwin-arm64: metal-ds4 nvidia: cuda13-ds4 nvidia-cuda-13: cuda13-ds4 nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ds4 uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-ds4 mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-ds4 - name: metal-ds4 alias: ds4 license: mit description: | antirez/ds4 - DeepSeek V4 Flash inference engine. Single-model, optimized for Metal (Darwin) and CUDA (Linux). Requires the GGUFs published at huggingface.co/antirez/deepseek-v4-gguf. urls: - https://github.com/antirez/ds4 tags: - text-to-text - LLM - CPU - CUDA - Metal capabilities: default: cpu-ds4 metal: metal-ds4 metal-darwin-arm64: metal-ds4 nvidia: cuda13-ds4 nvidia-cuda-13: cuda13-ds4 nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ds4 uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-ds4 mirrors: - localai/localai-backends:latest-metal-darwin-arm64-ds4 - name: metal-ds4-development alias: ds4 license: mit description: | antirez/ds4 - DeepSeek V4 Flash inference engine. Single-model, optimized for Metal (Darwin) and CUDA (Linux). Requires the GGUFs published at huggingface.co/antirez/deepseek-v4-gguf. urls: - https://github.com/antirez/ds4 tags: - text-to-text - LLM - CPU - CUDA - Metal capabilities: default: cpu-ds4 metal: metal-ds4 metal-darwin-arm64: metal-ds4 nvidia: cuda13-ds4 nvidia-cuda-13: cuda13-ds4 nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ds4 uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-ds4 mirrors: - localai/localai-backends:master-metal-darwin-arm64-ds4 - name: whisper-development alias: whisper license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | Port of OpenAI's Whisper model in C/C++ urls: - https://github.com/ggml-org/whisper.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-whisper-development default: cpu-whisper-development intel: intel-sycl-f16-whisper-development metal: metal-whisper-development nvidia: cuda12-whisper-development nvidia-cuda-12: cuda12-whisper-development nvidia-cuda-13: cuda13-whisper-development nvidia-l4t: nvidia-l4t-arm64-whisper-development nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper-development vulkan: vulkan-whisper-development - name: nvidia-l4t-arm64-whisper alias: whisper license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | Port of OpenAI's Whisper model in C/C++ urls: - https://github.com/ggml-org/whisper.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-whisper default: cpu-whisper intel: intel-sycl-f16-whisper metal: metal-whisper nvidia: cuda12-whisper nvidia-cuda-12: cuda12-whisper nvidia-cuda-13: cuda13-whisper nvidia-l4t: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper vulkan: vulkan-whisper uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-whisper mirrors: - localai/localai-backends:latest-nvidia-l4t-arm64-whisper - name: nvidia-l4t-arm64-whisper-development alias: whisper license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | Port of OpenAI's Whisper model in C/C++ urls: - https://github.com/ggml-org/whisper.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-whisper default: cpu-whisper intel: intel-sycl-f16-whisper metal: metal-whisper nvidia: cuda12-whisper nvidia-cuda-12: cuda12-whisper nvidia-cuda-13: cuda13-whisper nvidia-l4t: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper vulkan: vulkan-whisper uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-whisper mirrors: - localai/localai-backends:master-nvidia-l4t-arm64-whisper - name: cuda13-nvidia-l4t-arm64-whisper alias: whisper license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | Port of OpenAI's Whisper model in C/C++ urls: - https://github.com/ggml-org/whisper.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-whisper default: cpu-whisper intel: intel-sycl-f16-whisper metal: metal-whisper nvidia: cuda12-whisper nvidia-cuda-12: cuda12-whisper nvidia-cuda-13: cuda13-whisper nvidia-l4t: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper vulkan: vulkan-whisper uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-whisper mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-whisper - name: cuda13-nvidia-l4t-arm64-whisper-development alias: whisper license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | Port of OpenAI's Whisper model in C/C++ urls: - https://github.com/ggml-org/whisper.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-whisper default: cpu-whisper intel: intel-sycl-f16-whisper metal: metal-whisper nvidia: cuda12-whisper nvidia-cuda-12: cuda12-whisper nvidia-cuda-13: cuda13-whisper nvidia-l4t: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper vulkan: vulkan-whisper uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-whisper mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-whisper - name: cpu-whisper alias: whisper license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | Port of OpenAI's Whisper model in C/C++ urls: - https://github.com/ggml-org/whisper.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-whisper default: cpu-whisper intel: intel-sycl-f16-whisper metal: metal-whisper nvidia: cuda12-whisper nvidia-cuda-12: cuda12-whisper nvidia-cuda-13: cuda13-whisper nvidia-l4t: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper vulkan: vulkan-whisper uri: quay.io/go-skynet/local-ai-backends:latest-cpu-whisper mirrors: - localai/localai-backends:latest-cpu-whisper - name: metal-whisper alias: whisper license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | Port of OpenAI's Whisper model in C/C++ urls: - https://github.com/ggml-org/whisper.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-whisper default: cpu-whisper intel: intel-sycl-f16-whisper metal: metal-whisper nvidia: cuda12-whisper nvidia-cuda-12: cuda12-whisper nvidia-cuda-13: cuda13-whisper nvidia-l4t: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper vulkan: vulkan-whisper uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-whisper mirrors: - localai/localai-backends:latest-metal-darwin-arm64-whisper - name: metal-whisper-development alias: whisper license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | Port of OpenAI's Whisper model in C/C++ urls: - https://github.com/ggml-org/whisper.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-whisper default: cpu-whisper intel: intel-sycl-f16-whisper metal: metal-whisper nvidia: cuda12-whisper nvidia-cuda-12: cuda12-whisper nvidia-cuda-13: cuda13-whisper nvidia-l4t: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper vulkan: vulkan-whisper uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-whisper mirrors: - localai/localai-backends:master-metal-darwin-arm64-whisper - name: cpu-whisper-development alias: whisper license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | Port of OpenAI's Whisper model in C/C++ urls: - https://github.com/ggml-org/whisper.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-whisper default: cpu-whisper intel: intel-sycl-f16-whisper metal: metal-whisper nvidia: cuda12-whisper nvidia-cuda-12: cuda12-whisper nvidia-cuda-13: cuda13-whisper nvidia-l4t: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper vulkan: vulkan-whisper uri: quay.io/go-skynet/local-ai-backends:master-cpu-whisper mirrors: - localai/localai-backends:master-cpu-whisper - name: cuda12-whisper alias: whisper license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | Port of OpenAI's Whisper model in C/C++ urls: - https://github.com/ggml-org/whisper.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-whisper default: cpu-whisper intel: intel-sycl-f16-whisper metal: metal-whisper nvidia: cuda12-whisper nvidia-cuda-12: cuda12-whisper nvidia-cuda-13: cuda13-whisper nvidia-l4t: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper vulkan: vulkan-whisper uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-whisper mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-whisper - name: rocm-whisper alias: whisper license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | Port of OpenAI's Whisper model in C/C++ urls: - https://github.com/ggml-org/whisper.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-whisper default: cpu-whisper intel: intel-sycl-f16-whisper metal: metal-whisper nvidia: cuda12-whisper nvidia-cuda-12: cuda12-whisper nvidia-cuda-13: cuda13-whisper nvidia-l4t: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper vulkan: vulkan-whisper uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-whisper mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-whisper - name: intel-sycl-f32-whisper alias: whisper license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | Port of OpenAI's Whisper model in C/C++ urls: - https://github.com/ggml-org/whisper.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-whisper default: cpu-whisper intel: intel-sycl-f16-whisper metal: metal-whisper nvidia: cuda12-whisper nvidia-cuda-12: cuda12-whisper nvidia-cuda-13: cuda13-whisper nvidia-l4t: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper vulkan: vulkan-whisper uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-whisper mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f32-whisper - name: intel-sycl-f16-whisper alias: whisper license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | Port of OpenAI's Whisper model in C/C++ urls: - https://github.com/ggml-org/whisper.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-whisper default: cpu-whisper intel: intel-sycl-f16-whisper metal: metal-whisper nvidia: cuda12-whisper nvidia-cuda-12: cuda12-whisper nvidia-cuda-13: cuda13-whisper nvidia-l4t: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper vulkan: vulkan-whisper uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-whisper mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f16-whisper - name: vulkan-whisper alias: whisper license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | Port of OpenAI's Whisper model in C/C++ urls: - https://github.com/ggml-org/whisper.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-whisper default: cpu-whisper intel: intel-sycl-f16-whisper metal: metal-whisper nvidia: cuda12-whisper nvidia-cuda-12: cuda12-whisper nvidia-cuda-13: cuda13-whisper nvidia-l4t: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper vulkan: vulkan-whisper uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-whisper mirrors: - localai/localai-backends:latest-gpu-vulkan-whisper - name: vulkan-whisper-development alias: whisper license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | Port of OpenAI's Whisper model in C/C++ urls: - https://github.com/ggml-org/whisper.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-whisper default: cpu-whisper intel: intel-sycl-f16-whisper metal: metal-whisper nvidia: cuda12-whisper nvidia-cuda-12: cuda12-whisper nvidia-cuda-13: cuda13-whisper nvidia-l4t: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper vulkan: vulkan-whisper uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-whisper mirrors: - localai/localai-backends:master-gpu-vulkan-whisper - name: cuda12-whisper-development alias: whisper license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | Port of OpenAI's Whisper model in C/C++ urls: - https://github.com/ggml-org/whisper.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-whisper default: cpu-whisper intel: intel-sycl-f16-whisper metal: metal-whisper nvidia: cuda12-whisper nvidia-cuda-12: cuda12-whisper nvidia-cuda-13: cuda13-whisper nvidia-l4t: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper vulkan: vulkan-whisper uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-whisper mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-whisper - name: rocm-whisper-development alias: whisper license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | Port of OpenAI's Whisper model in C/C++ urls: - https://github.com/ggml-org/whisper.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-whisper default: cpu-whisper intel: intel-sycl-f16-whisper metal: metal-whisper nvidia: cuda12-whisper nvidia-cuda-12: cuda12-whisper nvidia-cuda-13: cuda13-whisper nvidia-l4t: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper vulkan: vulkan-whisper uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-whisper mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-whisper - name: intel-sycl-f32-whisper-development alias: whisper license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | Port of OpenAI's Whisper model in C/C++ urls: - https://github.com/ggml-org/whisper.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-whisper default: cpu-whisper intel: intel-sycl-f16-whisper metal: metal-whisper nvidia: cuda12-whisper nvidia-cuda-12: cuda12-whisper nvidia-cuda-13: cuda13-whisper nvidia-l4t: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper vulkan: vulkan-whisper uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-whisper mirrors: - localai/localai-backends:master-gpu-intel-sycl-f32-whisper - name: intel-sycl-f16-whisper-development alias: whisper license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | Port of OpenAI's Whisper model in C/C++ urls: - https://github.com/ggml-org/whisper.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-whisper default: cpu-whisper intel: intel-sycl-f16-whisper metal: metal-whisper nvidia: cuda12-whisper nvidia-cuda-12: cuda12-whisper nvidia-cuda-13: cuda13-whisper nvidia-l4t: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper vulkan: vulkan-whisper uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-whisper mirrors: - localai/localai-backends:master-gpu-intel-sycl-f16-whisper - name: cuda13-whisper alias: whisper license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | Port of OpenAI's Whisper model in C/C++ urls: - https://github.com/ggml-org/whisper.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-whisper default: cpu-whisper intel: intel-sycl-f16-whisper metal: metal-whisper nvidia: cuda12-whisper nvidia-cuda-12: cuda12-whisper nvidia-cuda-13: cuda13-whisper nvidia-l4t: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper vulkan: vulkan-whisper uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-whisper mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-whisper - name: cuda13-whisper-development alias: whisper license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | Port of OpenAI's Whisper model in C/C++ urls: - https://github.com/ggml-org/whisper.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-whisper default: cpu-whisper intel: intel-sycl-f16-whisper metal: metal-whisper nvidia: cuda12-whisper nvidia-cuda-12: cuda12-whisper nvidia-cuda-13: cuda13-whisper nvidia-l4t: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisper nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-whisper vulkan: vulkan-whisper uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-whisper mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-whisper - name: crispasr-development alias: crispasr license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more). urls: - https://github.com/CrispStrobe/CrispASR tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-crispasr-development default: cpu-crispasr-development intel: intel-sycl-f16-crispasr-development metal: metal-crispasr-development nvidia: cuda12-crispasr-development nvidia-cuda-12: cuda12-crispasr-development nvidia-cuda-13: cuda13-crispasr-development nvidia-l4t: nvidia-l4t-arm64-crispasr-development nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr-development vulkan: vulkan-crispasr-development - name: nvidia-l4t-arm64-crispasr alias: crispasr license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more). urls: - https://github.com/CrispStrobe/CrispASR tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-crispasr default: cpu-crispasr intel: intel-sycl-f16-crispasr metal: metal-crispasr nvidia: cuda12-crispasr nvidia-cuda-12: cuda12-crispasr nvidia-cuda-13: cuda13-crispasr nvidia-l4t: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr vulkan: vulkan-crispasr uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-crispasr mirrors: - localai/localai-backends:latest-nvidia-l4t-arm64-crispasr - name: nvidia-l4t-arm64-crispasr-development alias: crispasr license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more). urls: - https://github.com/CrispStrobe/CrispASR tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-crispasr default: cpu-crispasr intel: intel-sycl-f16-crispasr metal: metal-crispasr nvidia: cuda12-crispasr nvidia-cuda-12: cuda12-crispasr nvidia-cuda-13: cuda13-crispasr nvidia-l4t: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr vulkan: vulkan-crispasr uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-crispasr mirrors: - localai/localai-backends:master-nvidia-l4t-arm64-crispasr - name: cuda13-nvidia-l4t-arm64-crispasr alias: crispasr license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more). urls: - https://github.com/CrispStrobe/CrispASR tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-crispasr default: cpu-crispasr intel: intel-sycl-f16-crispasr metal: metal-crispasr nvidia: cuda12-crispasr nvidia-cuda-12: cuda12-crispasr nvidia-cuda-13: cuda13-crispasr nvidia-l4t: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr vulkan: vulkan-crispasr uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-crispasr mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-crispasr - name: cuda13-nvidia-l4t-arm64-crispasr-development alias: crispasr license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more). urls: - https://github.com/CrispStrobe/CrispASR tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-crispasr default: cpu-crispasr intel: intel-sycl-f16-crispasr metal: metal-crispasr nvidia: cuda12-crispasr nvidia-cuda-12: cuda12-crispasr nvidia-cuda-13: cuda13-crispasr nvidia-l4t: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr vulkan: vulkan-crispasr uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-crispasr mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-crispasr - name: cpu-crispasr alias: crispasr license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more). urls: - https://github.com/CrispStrobe/CrispASR tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-crispasr default: cpu-crispasr intel: intel-sycl-f16-crispasr metal: metal-crispasr nvidia: cuda12-crispasr nvidia-cuda-12: cuda12-crispasr nvidia-cuda-13: cuda13-crispasr nvidia-l4t: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr vulkan: vulkan-crispasr uri: quay.io/go-skynet/local-ai-backends:latest-cpu-crispasr mirrors: - localai/localai-backends:latest-cpu-crispasr - name: metal-crispasr alias: crispasr license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more). urls: - https://github.com/CrispStrobe/CrispASR tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-crispasr default: cpu-crispasr intel: intel-sycl-f16-crispasr metal: metal-crispasr nvidia: cuda12-crispasr nvidia-cuda-12: cuda12-crispasr nvidia-cuda-13: cuda13-crispasr nvidia-l4t: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr vulkan: vulkan-crispasr uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-crispasr mirrors: - localai/localai-backends:latest-metal-darwin-arm64-crispasr - name: metal-crispasr-development alias: crispasr license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more). urls: - https://github.com/CrispStrobe/CrispASR tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-crispasr default: cpu-crispasr intel: intel-sycl-f16-crispasr metal: metal-crispasr nvidia: cuda12-crispasr nvidia-cuda-12: cuda12-crispasr nvidia-cuda-13: cuda13-crispasr nvidia-l4t: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr vulkan: vulkan-crispasr uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-crispasr mirrors: - localai/localai-backends:master-metal-darwin-arm64-crispasr - name: cpu-crispasr-development alias: crispasr license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more). urls: - https://github.com/CrispStrobe/CrispASR tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-crispasr default: cpu-crispasr intel: intel-sycl-f16-crispasr metal: metal-crispasr nvidia: cuda12-crispasr nvidia-cuda-12: cuda12-crispasr nvidia-cuda-13: cuda13-crispasr nvidia-l4t: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr vulkan: vulkan-crispasr uri: quay.io/go-skynet/local-ai-backends:master-cpu-crispasr mirrors: - localai/localai-backends:master-cpu-crispasr - name: cuda12-crispasr alias: crispasr license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more). urls: - https://github.com/CrispStrobe/CrispASR tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-crispasr default: cpu-crispasr intel: intel-sycl-f16-crispasr metal: metal-crispasr nvidia: cuda12-crispasr nvidia-cuda-12: cuda12-crispasr nvidia-cuda-13: cuda13-crispasr nvidia-l4t: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr vulkan: vulkan-crispasr uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-crispasr mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-crispasr - name: rocm-crispasr alias: crispasr license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more). urls: - https://github.com/CrispStrobe/CrispASR tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-crispasr default: cpu-crispasr intel: intel-sycl-f16-crispasr metal: metal-crispasr nvidia: cuda12-crispasr nvidia-cuda-12: cuda12-crispasr nvidia-cuda-13: cuda13-crispasr nvidia-l4t: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr vulkan: vulkan-crispasr uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-crispasr mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-crispasr - name: intel-sycl-f32-crispasr alias: crispasr license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more). urls: - https://github.com/CrispStrobe/CrispASR tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-crispasr default: cpu-crispasr intel: intel-sycl-f16-crispasr metal: metal-crispasr nvidia: cuda12-crispasr nvidia-cuda-12: cuda12-crispasr nvidia-cuda-13: cuda13-crispasr nvidia-l4t: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr vulkan: vulkan-crispasr uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-crispasr mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f32-crispasr - name: intel-sycl-f16-crispasr alias: crispasr license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more). urls: - https://github.com/CrispStrobe/CrispASR tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-crispasr default: cpu-crispasr intel: intel-sycl-f16-crispasr metal: metal-crispasr nvidia: cuda12-crispasr nvidia-cuda-12: cuda12-crispasr nvidia-cuda-13: cuda13-crispasr nvidia-l4t: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr vulkan: vulkan-crispasr uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-crispasr mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f16-crispasr - name: vulkan-crispasr alias: crispasr license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more). urls: - https://github.com/CrispStrobe/CrispASR tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-crispasr default: cpu-crispasr intel: intel-sycl-f16-crispasr metal: metal-crispasr nvidia: cuda12-crispasr nvidia-cuda-12: cuda12-crispasr nvidia-cuda-13: cuda13-crispasr nvidia-l4t: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr vulkan: vulkan-crispasr uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-crispasr mirrors: - localai/localai-backends:latest-gpu-vulkan-crispasr - name: vulkan-crispasr-development alias: crispasr license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more). urls: - https://github.com/CrispStrobe/CrispASR tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-crispasr default: cpu-crispasr intel: intel-sycl-f16-crispasr metal: metal-crispasr nvidia: cuda12-crispasr nvidia-cuda-12: cuda12-crispasr nvidia-cuda-13: cuda13-crispasr nvidia-l4t: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr vulkan: vulkan-crispasr uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-crispasr mirrors: - localai/localai-backends:master-gpu-vulkan-crispasr - name: cuda12-crispasr-development alias: crispasr license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more). urls: - https://github.com/CrispStrobe/CrispASR tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-crispasr default: cpu-crispasr intel: intel-sycl-f16-crispasr metal: metal-crispasr nvidia: cuda12-crispasr nvidia-cuda-12: cuda12-crispasr nvidia-cuda-13: cuda13-crispasr nvidia-l4t: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr vulkan: vulkan-crispasr uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-crispasr mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-crispasr - name: rocm-crispasr-development alias: crispasr license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more). urls: - https://github.com/CrispStrobe/CrispASR tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-crispasr default: cpu-crispasr intel: intel-sycl-f16-crispasr metal: metal-crispasr nvidia: cuda12-crispasr nvidia-cuda-12: cuda12-crispasr nvidia-cuda-13: cuda13-crispasr nvidia-l4t: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr vulkan: vulkan-crispasr uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-crispasr mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-crispasr - name: intel-sycl-f32-crispasr-development alias: crispasr license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more). urls: - https://github.com/CrispStrobe/CrispASR tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-crispasr default: cpu-crispasr intel: intel-sycl-f16-crispasr metal: metal-crispasr nvidia: cuda12-crispasr nvidia-cuda-12: cuda12-crispasr nvidia-cuda-13: cuda13-crispasr nvidia-l4t: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr vulkan: vulkan-crispasr uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-crispasr mirrors: - localai/localai-backends:master-gpu-intel-sycl-f32-crispasr - name: intel-sycl-f16-crispasr-development alias: crispasr license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more). urls: - https://github.com/CrispStrobe/CrispASR tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-crispasr default: cpu-crispasr intel: intel-sycl-f16-crispasr metal: metal-crispasr nvidia: cuda12-crispasr nvidia-cuda-12: cuda12-crispasr nvidia-cuda-13: cuda13-crispasr nvidia-l4t: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr vulkan: vulkan-crispasr uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-crispasr mirrors: - localai/localai-backends:master-gpu-intel-sycl-f16-crispasr - name: cuda13-crispasr alias: crispasr license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more). urls: - https://github.com/CrispStrobe/CrispASR tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-crispasr default: cpu-crispasr intel: intel-sycl-f16-crispasr metal: metal-crispasr nvidia: cuda12-crispasr nvidia-cuda-12: cuda12-crispasr nvidia-cuda-13: cuda13-crispasr nvidia-l4t: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr vulkan: vulkan-crispasr uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-crispasr mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-crispasr - name: cuda13-crispasr-development alias: crispasr license: mit icon: https://user-images.githubusercontent.com/1991296/235238348-05d0f6a4-da44-4900-a1de-d0707e75b763.jpeg description: | CrispASR unified speech engine (whisper.cpp fork on ggml) supporting many ASR architectures (Parakeet, Canary, Voxtral, Qwen3-ASR, Granite, Wav2Vec2, Moonshine, OmniASR, FireRedASR, and more). urls: - https://github.com/CrispStrobe/CrispASR tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-crispasr default: cpu-crispasr intel: intel-sycl-f16-crispasr metal: metal-crispasr nvidia: cuda12-crispasr nvidia-cuda-12: cuda12-crispasr nvidia-cuda-13: cuda13-crispasr nvidia-l4t: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-12: nvidia-l4t-arm64-crispasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-crispasr vulkan: vulkan-crispasr uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-crispasr mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-crispasr - name: parakeet-cpp-development alias: parakeet-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models. It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/parakeet.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-parakeet-cpp-development default: cpu-parakeet-cpp-development intel: intel-sycl-f16-parakeet-cpp-development metal: metal-parakeet-cpp-development nvidia: cuda12-parakeet-cpp-development nvidia-cuda-12: cuda12-parakeet-cpp-development nvidia-cuda-13: cuda13-parakeet-cpp-development nvidia-l4t: nvidia-l4t-arm64-parakeet-cpp-development nvidia-l4t-cuda-12: nvidia-l4t-arm64-parakeet-cpp-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-parakeet-cpp-development vulkan: vulkan-parakeet-cpp-development - name: nvidia-l4t-arm64-parakeet-cpp alias: parakeet-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models. It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/parakeet.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-parakeet-cpp default: cpu-parakeet-cpp intel: intel-sycl-f16-parakeet-cpp metal: metal-parakeet-cpp nvidia: cuda12-parakeet-cpp nvidia-cuda-12: cuda12-parakeet-cpp nvidia-cuda-13: cuda13-parakeet-cpp nvidia-l4t: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-parakeet-cpp vulkan: vulkan-parakeet-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-parakeet-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-arm64-parakeet-cpp - name: nvidia-l4t-arm64-parakeet-cpp-development alias: parakeet-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models. It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/parakeet.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-parakeet-cpp default: cpu-parakeet-cpp intel: intel-sycl-f16-parakeet-cpp metal: metal-parakeet-cpp nvidia: cuda12-parakeet-cpp nvidia-cuda-12: cuda12-parakeet-cpp nvidia-cuda-13: cuda13-parakeet-cpp nvidia-l4t: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-parakeet-cpp vulkan: vulkan-parakeet-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-parakeet-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-arm64-parakeet-cpp - name: cuda13-nvidia-l4t-arm64-parakeet-cpp alias: parakeet-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models. It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/parakeet.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-parakeet-cpp default: cpu-parakeet-cpp intel: intel-sycl-f16-parakeet-cpp metal: metal-parakeet-cpp nvidia: cuda12-parakeet-cpp nvidia-cuda-12: cuda12-parakeet-cpp nvidia-cuda-13: cuda13-parakeet-cpp nvidia-l4t: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-parakeet-cpp vulkan: vulkan-parakeet-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-parakeet-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-parakeet-cpp - name: cuda13-nvidia-l4t-arm64-parakeet-cpp-development alias: parakeet-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models. It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/parakeet.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-parakeet-cpp default: cpu-parakeet-cpp intel: intel-sycl-f16-parakeet-cpp metal: metal-parakeet-cpp nvidia: cuda12-parakeet-cpp nvidia-cuda-12: cuda12-parakeet-cpp nvidia-cuda-13: cuda13-parakeet-cpp nvidia-l4t: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-parakeet-cpp vulkan: vulkan-parakeet-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-parakeet-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-parakeet-cpp - name: cpu-parakeet-cpp alias: parakeet-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models. It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/parakeet.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-parakeet-cpp default: cpu-parakeet-cpp intel: intel-sycl-f16-parakeet-cpp metal: metal-parakeet-cpp nvidia: cuda12-parakeet-cpp nvidia-cuda-12: cuda12-parakeet-cpp nvidia-cuda-13: cuda13-parakeet-cpp nvidia-l4t: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-parakeet-cpp vulkan: vulkan-parakeet-cpp uri: quay.io/go-skynet/local-ai-backends:latest-cpu-parakeet-cpp mirrors: - localai/localai-backends:latest-cpu-parakeet-cpp - name: cpu-parakeet-cpp-development alias: parakeet-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models. It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/parakeet.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-parakeet-cpp default: cpu-parakeet-cpp intel: intel-sycl-f16-parakeet-cpp metal: metal-parakeet-cpp nvidia: cuda12-parakeet-cpp nvidia-cuda-12: cuda12-parakeet-cpp nvidia-cuda-13: cuda13-parakeet-cpp nvidia-l4t: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-parakeet-cpp vulkan: vulkan-parakeet-cpp uri: quay.io/go-skynet/local-ai-backends:master-cpu-parakeet-cpp mirrors: - localai/localai-backends:master-cpu-parakeet-cpp - name: metal-parakeet-cpp alias: parakeet-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models. It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/parakeet.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-parakeet-cpp default: cpu-parakeet-cpp intel: intel-sycl-f16-parakeet-cpp metal: metal-parakeet-cpp nvidia: cuda12-parakeet-cpp nvidia-cuda-12: cuda12-parakeet-cpp nvidia-cuda-13: cuda13-parakeet-cpp nvidia-l4t: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-parakeet-cpp vulkan: vulkan-parakeet-cpp uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-parakeet-cpp mirrors: - localai/localai-backends:latest-metal-darwin-arm64-parakeet-cpp - name: metal-parakeet-cpp-development alias: parakeet-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models. It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/parakeet.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-parakeet-cpp default: cpu-parakeet-cpp intel: intel-sycl-f16-parakeet-cpp metal: metal-parakeet-cpp nvidia: cuda12-parakeet-cpp nvidia-cuda-12: cuda12-parakeet-cpp nvidia-cuda-13: cuda13-parakeet-cpp nvidia-l4t: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-parakeet-cpp vulkan: vulkan-parakeet-cpp uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-parakeet-cpp mirrors: - localai/localai-backends:master-metal-darwin-arm64-parakeet-cpp - name: cuda12-parakeet-cpp alias: parakeet-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models. It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/parakeet.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-parakeet-cpp default: cpu-parakeet-cpp intel: intel-sycl-f16-parakeet-cpp metal: metal-parakeet-cpp nvidia: cuda12-parakeet-cpp nvidia-cuda-12: cuda12-parakeet-cpp nvidia-cuda-13: cuda13-parakeet-cpp nvidia-l4t: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-parakeet-cpp vulkan: vulkan-parakeet-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-parakeet-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-parakeet-cpp - name: cuda12-parakeet-cpp-development alias: parakeet-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models. It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/parakeet.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-parakeet-cpp default: cpu-parakeet-cpp intel: intel-sycl-f16-parakeet-cpp metal: metal-parakeet-cpp nvidia: cuda12-parakeet-cpp nvidia-cuda-12: cuda12-parakeet-cpp nvidia-cuda-13: cuda13-parakeet-cpp nvidia-l4t: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-parakeet-cpp vulkan: vulkan-parakeet-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-parakeet-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-parakeet-cpp - name: rocm-parakeet-cpp alias: parakeet-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models. It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/parakeet.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-parakeet-cpp default: cpu-parakeet-cpp intel: intel-sycl-f16-parakeet-cpp metal: metal-parakeet-cpp nvidia: cuda12-parakeet-cpp nvidia-cuda-12: cuda12-parakeet-cpp nvidia-cuda-13: cuda13-parakeet-cpp nvidia-l4t: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-parakeet-cpp vulkan: vulkan-parakeet-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-parakeet-cpp mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-parakeet-cpp - name: rocm-parakeet-cpp-development alias: parakeet-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models. It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/parakeet.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-parakeet-cpp default: cpu-parakeet-cpp intel: intel-sycl-f16-parakeet-cpp metal: metal-parakeet-cpp nvidia: cuda12-parakeet-cpp nvidia-cuda-12: cuda12-parakeet-cpp nvidia-cuda-13: cuda13-parakeet-cpp nvidia-l4t: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-parakeet-cpp vulkan: vulkan-parakeet-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-parakeet-cpp mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-parakeet-cpp - name: intel-sycl-f32-parakeet-cpp alias: parakeet-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models. It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/parakeet.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-parakeet-cpp default: cpu-parakeet-cpp intel: intel-sycl-f16-parakeet-cpp metal: metal-parakeet-cpp nvidia: cuda12-parakeet-cpp nvidia-cuda-12: cuda12-parakeet-cpp nvidia-cuda-13: cuda13-parakeet-cpp nvidia-l4t: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-parakeet-cpp vulkan: vulkan-parakeet-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-parakeet-cpp mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f32-parakeet-cpp - name: intel-sycl-f32-parakeet-cpp-development alias: parakeet-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models. It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/parakeet.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-parakeet-cpp default: cpu-parakeet-cpp intel: intel-sycl-f16-parakeet-cpp metal: metal-parakeet-cpp nvidia: cuda12-parakeet-cpp nvidia-cuda-12: cuda12-parakeet-cpp nvidia-cuda-13: cuda13-parakeet-cpp nvidia-l4t: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-parakeet-cpp vulkan: vulkan-parakeet-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-parakeet-cpp mirrors: - localai/localai-backends:master-gpu-intel-sycl-f32-parakeet-cpp - name: intel-sycl-f16-parakeet-cpp alias: parakeet-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models. It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/parakeet.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-parakeet-cpp default: cpu-parakeet-cpp intel: intel-sycl-f16-parakeet-cpp metal: metal-parakeet-cpp nvidia: cuda12-parakeet-cpp nvidia-cuda-12: cuda12-parakeet-cpp nvidia-cuda-13: cuda13-parakeet-cpp nvidia-l4t: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-parakeet-cpp vulkan: vulkan-parakeet-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-parakeet-cpp mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f16-parakeet-cpp - name: intel-sycl-f16-parakeet-cpp-development alias: parakeet-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models. It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/parakeet.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-parakeet-cpp default: cpu-parakeet-cpp intel: intel-sycl-f16-parakeet-cpp metal: metal-parakeet-cpp nvidia: cuda12-parakeet-cpp nvidia-cuda-12: cuda12-parakeet-cpp nvidia-cuda-13: cuda13-parakeet-cpp nvidia-l4t: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-parakeet-cpp vulkan: vulkan-parakeet-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-parakeet-cpp mirrors: - localai/localai-backends:master-gpu-intel-sycl-f16-parakeet-cpp - name: vulkan-parakeet-cpp alias: parakeet-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models. It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/parakeet.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-parakeet-cpp default: cpu-parakeet-cpp intel: intel-sycl-f16-parakeet-cpp metal: metal-parakeet-cpp nvidia: cuda12-parakeet-cpp nvidia-cuda-12: cuda12-parakeet-cpp nvidia-cuda-13: cuda13-parakeet-cpp nvidia-l4t: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-parakeet-cpp vulkan: vulkan-parakeet-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-parakeet-cpp mirrors: - localai/localai-backends:latest-gpu-vulkan-parakeet-cpp - name: vulkan-parakeet-cpp-development alias: parakeet-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models. It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/parakeet.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-parakeet-cpp default: cpu-parakeet-cpp intel: intel-sycl-f16-parakeet-cpp metal: metal-parakeet-cpp nvidia: cuda12-parakeet-cpp nvidia-cuda-12: cuda12-parakeet-cpp nvidia-cuda-13: cuda13-parakeet-cpp nvidia-l4t: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-parakeet-cpp vulkan: vulkan-parakeet-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-parakeet-cpp mirrors: - localai/localai-backends:master-gpu-vulkan-parakeet-cpp - name: cuda13-parakeet-cpp alias: parakeet-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models. It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/parakeet.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-parakeet-cpp default: cpu-parakeet-cpp intel: intel-sycl-f16-parakeet-cpp metal: metal-parakeet-cpp nvidia: cuda12-parakeet-cpp nvidia-cuda-12: cuda12-parakeet-cpp nvidia-cuda-13: cuda13-parakeet-cpp nvidia-l4t: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-parakeet-cpp vulkan: vulkan-parakeet-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-parakeet-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-parakeet-cpp - name: cuda13-parakeet-cpp-development alias: parakeet-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | parakeet.cpp is a C++/ggml port of NVIDIA NeMo Parakeet automatic speech recognition (ASR) models. It supports the tdt, ctc, rnnt and hybrid decoder families as well as cache-aware streaming transcription, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/parakeet.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-parakeet-cpp default: cpu-parakeet-cpp intel: intel-sycl-f16-parakeet-cpp metal: metal-parakeet-cpp nvidia: cuda12-parakeet-cpp nvidia-cuda-12: cuda12-parakeet-cpp nvidia-cuda-13: cuda13-parakeet-cpp nvidia-l4t: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-parakeet-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-parakeet-cpp vulkan: vulkan-parakeet-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-parakeet-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-parakeet-cpp - name: nemo-speech-cpp-development alias: nemo-speech-cpp license: apache-2.0 icon: https://avatars.githubusercontent.com/u/1728152?s=200&v=4 description: | NVIDIA NeMo-Speech.cpp, a C++/ggml runtime for NVIDIA Nemotron Speech models. One backend serves four model families, selected automatically from the GGUF general.architecture key: automatic speech recognition (offline, cache-aware streaming and live transcription, with optional Silero VAD, punctuation, inverse text normalization and Sortformer speaker diarization attached), standalone Sortformer diarization, MagpieTTS text-to-speech over NanoCodec, and Riva-Translate text translation. Runs on CPU, NVIDIA CUDA, Vulkan, NVIDIA Jetson (L4T) and Apple Metal. urls: - https://github.com/NVIDIA/NeMo-Speech.cpp tags: - audio-transcription - text-to-speech - diarization - text-to-text - CPU - GPU - CUDA - Metal capabilities: default: cpu-nemo-speech-cpp-development metal: metal-nemo-speech-cpp-development nvidia: cuda12-nemo-speech-cpp-development nvidia-cuda-12: cuda12-nemo-speech-cpp-development nvidia-cuda-13: cuda13-nemo-speech-cpp-development nvidia-l4t: nvidia-l4t-arm64-nemo-speech-cpp-development nvidia-l4t-cuda-12: nvidia-l4t-arm64-nemo-speech-cpp-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-nemo-speech-cpp-development vulkan: vulkan-nemo-speech-cpp-development - name: cpu-nemo-speech-cpp alias: nemo-speech-cpp license: apache-2.0 icon: https://avatars.githubusercontent.com/u/1728152?s=200&v=4 description: | NVIDIA NeMo-Speech.cpp, a C++/ggml runtime for NVIDIA Nemotron Speech models. One backend serves four model families, selected automatically from the GGUF general.architecture key: automatic speech recognition (offline, cache-aware streaming and live transcription, with optional Silero VAD, punctuation, inverse text normalization and Sortformer speaker diarization attached), standalone Sortformer diarization, MagpieTTS text-to-speech over NanoCodec, and Riva-Translate text translation. Runs on CPU, NVIDIA CUDA, Vulkan, NVIDIA Jetson (L4T) and Apple Metal. urls: - https://github.com/NVIDIA/NeMo-Speech.cpp tags: - audio-transcription - text-to-speech - diarization - text-to-text - CPU - GPU - CUDA - Metal capabilities: default: cpu-nemo-speech-cpp metal: metal-nemo-speech-cpp nvidia: cuda12-nemo-speech-cpp nvidia-cuda-12: cuda12-nemo-speech-cpp nvidia-cuda-13: cuda13-nemo-speech-cpp nvidia-l4t: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-nemo-speech-cpp vulkan: vulkan-nemo-speech-cpp uri: quay.io/go-skynet/local-ai-backends:latest-cpu-nemo-speech-cpp mirrors: - localai/localai-backends:latest-cpu-nemo-speech-cpp - name: cpu-nemo-speech-cpp-development alias: nemo-speech-cpp license: apache-2.0 icon: https://avatars.githubusercontent.com/u/1728152?s=200&v=4 description: | NVIDIA NeMo-Speech.cpp, a C++/ggml runtime for NVIDIA Nemotron Speech models. One backend serves four model families, selected automatically from the GGUF general.architecture key: automatic speech recognition (offline, cache-aware streaming and live transcription, with optional Silero VAD, punctuation, inverse text normalization and Sortformer speaker diarization attached), standalone Sortformer diarization, MagpieTTS text-to-speech over NanoCodec, and Riva-Translate text translation. Runs on CPU, NVIDIA CUDA, Vulkan, NVIDIA Jetson (L4T) and Apple Metal. urls: - https://github.com/NVIDIA/NeMo-Speech.cpp tags: - audio-transcription - text-to-speech - diarization - text-to-text - CPU - GPU - CUDA - Metal capabilities: default: cpu-nemo-speech-cpp metal: metal-nemo-speech-cpp nvidia: cuda12-nemo-speech-cpp nvidia-cuda-12: cuda12-nemo-speech-cpp nvidia-cuda-13: cuda13-nemo-speech-cpp nvidia-l4t: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-nemo-speech-cpp vulkan: vulkan-nemo-speech-cpp uri: quay.io/go-skynet/local-ai-backends:master-cpu-nemo-speech-cpp mirrors: - localai/localai-backends:master-cpu-nemo-speech-cpp - name: cuda12-nemo-speech-cpp alias: nemo-speech-cpp license: apache-2.0 icon: https://avatars.githubusercontent.com/u/1728152?s=200&v=4 description: | NVIDIA NeMo-Speech.cpp, a C++/ggml runtime for NVIDIA Nemotron Speech models. One backend serves four model families, selected automatically from the GGUF general.architecture key: automatic speech recognition (offline, cache-aware streaming and live transcription, with optional Silero VAD, punctuation, inverse text normalization and Sortformer speaker diarization attached), standalone Sortformer diarization, MagpieTTS text-to-speech over NanoCodec, and Riva-Translate text translation. Runs on CPU, NVIDIA CUDA, Vulkan, NVIDIA Jetson (L4T) and Apple Metal. urls: - https://github.com/NVIDIA/NeMo-Speech.cpp tags: - audio-transcription - text-to-speech - diarization - text-to-text - CPU - GPU - CUDA - Metal capabilities: default: cpu-nemo-speech-cpp metal: metal-nemo-speech-cpp nvidia: cuda12-nemo-speech-cpp nvidia-cuda-12: cuda12-nemo-speech-cpp nvidia-cuda-13: cuda13-nemo-speech-cpp nvidia-l4t: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-nemo-speech-cpp vulkan: vulkan-nemo-speech-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-nemo-speech-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-nemo-speech-cpp - name: cuda12-nemo-speech-cpp-development alias: nemo-speech-cpp license: apache-2.0 icon: https://avatars.githubusercontent.com/u/1728152?s=200&v=4 description: | NVIDIA NeMo-Speech.cpp, a C++/ggml runtime for NVIDIA Nemotron Speech models. One backend serves four model families, selected automatically from the GGUF general.architecture key: automatic speech recognition (offline, cache-aware streaming and live transcription, with optional Silero VAD, punctuation, inverse text normalization and Sortformer speaker diarization attached), standalone Sortformer diarization, MagpieTTS text-to-speech over NanoCodec, and Riva-Translate text translation. Runs on CPU, NVIDIA CUDA, Vulkan, NVIDIA Jetson (L4T) and Apple Metal. urls: - https://github.com/NVIDIA/NeMo-Speech.cpp tags: - audio-transcription - text-to-speech - diarization - text-to-text - CPU - GPU - CUDA - Metal capabilities: default: cpu-nemo-speech-cpp metal: metal-nemo-speech-cpp nvidia: cuda12-nemo-speech-cpp nvidia-cuda-12: cuda12-nemo-speech-cpp nvidia-cuda-13: cuda13-nemo-speech-cpp nvidia-l4t: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-nemo-speech-cpp vulkan: vulkan-nemo-speech-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-nemo-speech-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-nemo-speech-cpp - name: cuda13-nemo-speech-cpp alias: nemo-speech-cpp license: apache-2.0 icon: https://avatars.githubusercontent.com/u/1728152?s=200&v=4 description: | NVIDIA NeMo-Speech.cpp, a C++/ggml runtime for NVIDIA Nemotron Speech models. One backend serves four model families, selected automatically from the GGUF general.architecture key: automatic speech recognition (offline, cache-aware streaming and live transcription, with optional Silero VAD, punctuation, inverse text normalization and Sortformer speaker diarization attached), standalone Sortformer diarization, MagpieTTS text-to-speech over NanoCodec, and Riva-Translate text translation. Runs on CPU, NVIDIA CUDA, Vulkan, NVIDIA Jetson (L4T) and Apple Metal. urls: - https://github.com/NVIDIA/NeMo-Speech.cpp tags: - audio-transcription - text-to-speech - diarization - text-to-text - CPU - GPU - CUDA - Metal capabilities: default: cpu-nemo-speech-cpp metal: metal-nemo-speech-cpp nvidia: cuda12-nemo-speech-cpp nvidia-cuda-12: cuda12-nemo-speech-cpp nvidia-cuda-13: cuda13-nemo-speech-cpp nvidia-l4t: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-nemo-speech-cpp vulkan: vulkan-nemo-speech-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-nemo-speech-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-nemo-speech-cpp - name: cuda13-nemo-speech-cpp-development alias: nemo-speech-cpp license: apache-2.0 icon: https://avatars.githubusercontent.com/u/1728152?s=200&v=4 description: | NVIDIA NeMo-Speech.cpp, a C++/ggml runtime for NVIDIA Nemotron Speech models. One backend serves four model families, selected automatically from the GGUF general.architecture key: automatic speech recognition (offline, cache-aware streaming and live transcription, with optional Silero VAD, punctuation, inverse text normalization and Sortformer speaker diarization attached), standalone Sortformer diarization, MagpieTTS text-to-speech over NanoCodec, and Riva-Translate text translation. Runs on CPU, NVIDIA CUDA, Vulkan, NVIDIA Jetson (L4T) and Apple Metal. urls: - https://github.com/NVIDIA/NeMo-Speech.cpp tags: - audio-transcription - text-to-speech - diarization - text-to-text - CPU - GPU - CUDA - Metal capabilities: default: cpu-nemo-speech-cpp metal: metal-nemo-speech-cpp nvidia: cuda12-nemo-speech-cpp nvidia-cuda-12: cuda12-nemo-speech-cpp nvidia-cuda-13: cuda13-nemo-speech-cpp nvidia-l4t: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-nemo-speech-cpp vulkan: vulkan-nemo-speech-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-nemo-speech-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-nemo-speech-cpp - name: vulkan-nemo-speech-cpp alias: nemo-speech-cpp license: apache-2.0 icon: https://avatars.githubusercontent.com/u/1728152?s=200&v=4 description: | NVIDIA NeMo-Speech.cpp, a C++/ggml runtime for NVIDIA Nemotron Speech models. One backend serves four model families, selected automatically from the GGUF general.architecture key: automatic speech recognition (offline, cache-aware streaming and live transcription, with optional Silero VAD, punctuation, inverse text normalization and Sortformer speaker diarization attached), standalone Sortformer diarization, MagpieTTS text-to-speech over NanoCodec, and Riva-Translate text translation. Runs on CPU, NVIDIA CUDA, Vulkan, NVIDIA Jetson (L4T) and Apple Metal. urls: - https://github.com/NVIDIA/NeMo-Speech.cpp tags: - audio-transcription - text-to-speech - diarization - text-to-text - CPU - GPU - CUDA - Metal capabilities: default: cpu-nemo-speech-cpp metal: metal-nemo-speech-cpp nvidia: cuda12-nemo-speech-cpp nvidia-cuda-12: cuda12-nemo-speech-cpp nvidia-cuda-13: cuda13-nemo-speech-cpp nvidia-l4t: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-nemo-speech-cpp vulkan: vulkan-nemo-speech-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-nemo-speech-cpp mirrors: - localai/localai-backends:latest-gpu-vulkan-nemo-speech-cpp - name: vulkan-nemo-speech-cpp-development alias: nemo-speech-cpp license: apache-2.0 icon: https://avatars.githubusercontent.com/u/1728152?s=200&v=4 description: | NVIDIA NeMo-Speech.cpp, a C++/ggml runtime for NVIDIA Nemotron Speech models. One backend serves four model families, selected automatically from the GGUF general.architecture key: automatic speech recognition (offline, cache-aware streaming and live transcription, with optional Silero VAD, punctuation, inverse text normalization and Sortformer speaker diarization attached), standalone Sortformer diarization, MagpieTTS text-to-speech over NanoCodec, and Riva-Translate text translation. Runs on CPU, NVIDIA CUDA, Vulkan, NVIDIA Jetson (L4T) and Apple Metal. urls: - https://github.com/NVIDIA/NeMo-Speech.cpp tags: - audio-transcription - text-to-speech - diarization - text-to-text - CPU - GPU - CUDA - Metal capabilities: default: cpu-nemo-speech-cpp metal: metal-nemo-speech-cpp nvidia: cuda12-nemo-speech-cpp nvidia-cuda-12: cuda12-nemo-speech-cpp nvidia-cuda-13: cuda13-nemo-speech-cpp nvidia-l4t: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-nemo-speech-cpp vulkan: vulkan-nemo-speech-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-nemo-speech-cpp mirrors: - localai/localai-backends:master-gpu-vulkan-nemo-speech-cpp - name: nvidia-l4t-arm64-nemo-speech-cpp alias: nemo-speech-cpp license: apache-2.0 icon: https://avatars.githubusercontent.com/u/1728152?s=200&v=4 description: | NVIDIA NeMo-Speech.cpp, a C++/ggml runtime for NVIDIA Nemotron Speech models. One backend serves four model families, selected automatically from the GGUF general.architecture key: automatic speech recognition (offline, cache-aware streaming and live transcription, with optional Silero VAD, punctuation, inverse text normalization and Sortformer speaker diarization attached), standalone Sortformer diarization, MagpieTTS text-to-speech over NanoCodec, and Riva-Translate text translation. Runs on CPU, NVIDIA CUDA, Vulkan, NVIDIA Jetson (L4T) and Apple Metal. urls: - https://github.com/NVIDIA/NeMo-Speech.cpp tags: - audio-transcription - text-to-speech - diarization - text-to-text - CPU - GPU - CUDA - Metal capabilities: default: cpu-nemo-speech-cpp metal: metal-nemo-speech-cpp nvidia: cuda12-nemo-speech-cpp nvidia-cuda-12: cuda12-nemo-speech-cpp nvidia-cuda-13: cuda13-nemo-speech-cpp nvidia-l4t: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-nemo-speech-cpp vulkan: vulkan-nemo-speech-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-nemo-speech-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-arm64-nemo-speech-cpp - name: nvidia-l4t-arm64-nemo-speech-cpp-development alias: nemo-speech-cpp license: apache-2.0 icon: https://avatars.githubusercontent.com/u/1728152?s=200&v=4 description: | NVIDIA NeMo-Speech.cpp, a C++/ggml runtime for NVIDIA Nemotron Speech models. One backend serves four model families, selected automatically from the GGUF general.architecture key: automatic speech recognition (offline, cache-aware streaming and live transcription, with optional Silero VAD, punctuation, inverse text normalization and Sortformer speaker diarization attached), standalone Sortformer diarization, MagpieTTS text-to-speech over NanoCodec, and Riva-Translate text translation. Runs on CPU, NVIDIA CUDA, Vulkan, NVIDIA Jetson (L4T) and Apple Metal. urls: - https://github.com/NVIDIA/NeMo-Speech.cpp tags: - audio-transcription - text-to-speech - diarization - text-to-text - CPU - GPU - CUDA - Metal capabilities: default: cpu-nemo-speech-cpp metal: metal-nemo-speech-cpp nvidia: cuda12-nemo-speech-cpp nvidia-cuda-12: cuda12-nemo-speech-cpp nvidia-cuda-13: cuda13-nemo-speech-cpp nvidia-l4t: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-nemo-speech-cpp vulkan: vulkan-nemo-speech-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-nemo-speech-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-arm64-nemo-speech-cpp - name: cuda13-nvidia-l4t-arm64-nemo-speech-cpp alias: nemo-speech-cpp license: apache-2.0 icon: https://avatars.githubusercontent.com/u/1728152?s=200&v=4 description: | NVIDIA NeMo-Speech.cpp, a C++/ggml runtime for NVIDIA Nemotron Speech models. One backend serves four model families, selected automatically from the GGUF general.architecture key: automatic speech recognition (offline, cache-aware streaming and live transcription, with optional Silero VAD, punctuation, inverse text normalization and Sortformer speaker diarization attached), standalone Sortformer diarization, MagpieTTS text-to-speech over NanoCodec, and Riva-Translate text translation. Runs on CPU, NVIDIA CUDA, Vulkan, NVIDIA Jetson (L4T) and Apple Metal. urls: - https://github.com/NVIDIA/NeMo-Speech.cpp tags: - audio-transcription - text-to-speech - diarization - text-to-text - CPU - GPU - CUDA - Metal capabilities: default: cpu-nemo-speech-cpp metal: metal-nemo-speech-cpp nvidia: cuda12-nemo-speech-cpp nvidia-cuda-12: cuda12-nemo-speech-cpp nvidia-cuda-13: cuda13-nemo-speech-cpp nvidia-l4t: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-nemo-speech-cpp vulkan: vulkan-nemo-speech-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-nemo-speech-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-nemo-speech-cpp - name: cuda13-nvidia-l4t-arm64-nemo-speech-cpp-development alias: nemo-speech-cpp license: apache-2.0 icon: https://avatars.githubusercontent.com/u/1728152?s=200&v=4 description: | NVIDIA NeMo-Speech.cpp, a C++/ggml runtime for NVIDIA Nemotron Speech models. One backend serves four model families, selected automatically from the GGUF general.architecture key: automatic speech recognition (offline, cache-aware streaming and live transcription, with optional Silero VAD, punctuation, inverse text normalization and Sortformer speaker diarization attached), standalone Sortformer diarization, MagpieTTS text-to-speech over NanoCodec, and Riva-Translate text translation. Runs on CPU, NVIDIA CUDA, Vulkan, NVIDIA Jetson (L4T) and Apple Metal. urls: - https://github.com/NVIDIA/NeMo-Speech.cpp tags: - audio-transcription - text-to-speech - diarization - text-to-text - CPU - GPU - CUDA - Metal capabilities: default: cpu-nemo-speech-cpp metal: metal-nemo-speech-cpp nvidia: cuda12-nemo-speech-cpp nvidia-cuda-12: cuda12-nemo-speech-cpp nvidia-cuda-13: cuda13-nemo-speech-cpp nvidia-l4t: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-nemo-speech-cpp vulkan: vulkan-nemo-speech-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-nemo-speech-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-nemo-speech-cpp - name: metal-nemo-speech-cpp alias: nemo-speech-cpp license: apache-2.0 icon: https://avatars.githubusercontent.com/u/1728152?s=200&v=4 description: | NVIDIA NeMo-Speech.cpp, a C++/ggml runtime for NVIDIA Nemotron Speech models. One backend serves four model families, selected automatically from the GGUF general.architecture key: automatic speech recognition (offline, cache-aware streaming and live transcription, with optional Silero VAD, punctuation, inverse text normalization and Sortformer speaker diarization attached), standalone Sortformer diarization, MagpieTTS text-to-speech over NanoCodec, and Riva-Translate text translation. Runs on CPU, NVIDIA CUDA, Vulkan, NVIDIA Jetson (L4T) and Apple Metal. urls: - https://github.com/NVIDIA/NeMo-Speech.cpp tags: - audio-transcription - text-to-speech - diarization - text-to-text - CPU - GPU - CUDA - Metal capabilities: default: cpu-nemo-speech-cpp metal: metal-nemo-speech-cpp nvidia: cuda12-nemo-speech-cpp nvidia-cuda-12: cuda12-nemo-speech-cpp nvidia-cuda-13: cuda13-nemo-speech-cpp nvidia-l4t: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-nemo-speech-cpp vulkan: vulkan-nemo-speech-cpp uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-nemo-speech-cpp mirrors: - localai/localai-backends:latest-metal-darwin-arm64-nemo-speech-cpp - name: metal-nemo-speech-cpp-development alias: nemo-speech-cpp license: apache-2.0 icon: https://avatars.githubusercontent.com/u/1728152?s=200&v=4 description: | NVIDIA NeMo-Speech.cpp, a C++/ggml runtime for NVIDIA Nemotron Speech models. One backend serves four model families, selected automatically from the GGUF general.architecture key: automatic speech recognition (offline, cache-aware streaming and live transcription, with optional Silero VAD, punctuation, inverse text normalization and Sortformer speaker diarization attached), standalone Sortformer diarization, MagpieTTS text-to-speech over NanoCodec, and Riva-Translate text translation. Runs on CPU, NVIDIA CUDA, Vulkan, NVIDIA Jetson (L4T) and Apple Metal. urls: - https://github.com/NVIDIA/NeMo-Speech.cpp tags: - audio-transcription - text-to-speech - diarization - text-to-text - CPU - GPU - CUDA - Metal capabilities: default: cpu-nemo-speech-cpp metal: metal-nemo-speech-cpp nvidia: cuda12-nemo-speech-cpp nvidia-cuda-12: cuda12-nemo-speech-cpp nvidia-cuda-13: cuda13-nemo-speech-cpp nvidia-l4t: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-nemo-speech-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-nemo-speech-cpp vulkan: vulkan-nemo-speech-cpp uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-nemo-speech-cpp mirrors: - localai/localai-backends:master-metal-darwin-arm64-nemo-speech-cpp - name: moss-transcribe-cpp-development alias: moss-transcribe-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | moss-transcribe.cpp is a C++/ggml port of OpenMOSS MOSS-Transcribe-Diarize, an end-to-end audio understanding model. It does joint long-form transcription, speaker diarization and timestamping in a single pass, emitting a speaker-labelled, time-aligned transcript, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan, Apple Metal and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/moss-transcribe.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-moss-transcribe-cpp-development default: cpu-moss-transcribe-cpp-development intel: intel-sycl-f16-moss-transcribe-cpp-development metal: metal-moss-transcribe-cpp-development nvidia: cuda12-moss-transcribe-cpp-development nvidia-cuda-12: cuda12-moss-transcribe-cpp-development nvidia-cuda-13: cuda13-moss-transcribe-cpp-development nvidia-l4t: nvidia-l4t-arm64-moss-transcribe-cpp-development nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-transcribe-cpp-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-transcribe-cpp-development vulkan: vulkan-moss-transcribe-cpp-development - name: nvidia-l4t-arm64-moss-transcribe-cpp alias: moss-transcribe-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | moss-transcribe.cpp is a C++/ggml port of OpenMOSS MOSS-Transcribe-Diarize, an end-to-end audio understanding model. It does joint long-form transcription, speaker diarization and timestamping in a single pass, emitting a speaker-labelled, time-aligned transcript, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan, Apple Metal and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/moss-transcribe.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-moss-transcribe-cpp default: cpu-moss-transcribe-cpp intel: intel-sycl-f16-moss-transcribe-cpp metal: metal-moss-transcribe-cpp nvidia: cuda12-moss-transcribe-cpp nvidia-cuda-12: cuda12-moss-transcribe-cpp nvidia-cuda-13: cuda13-moss-transcribe-cpp nvidia-l4t: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-transcribe-cpp vulkan: vulkan-moss-transcribe-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-moss-transcribe-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-arm64-moss-transcribe-cpp - name: nvidia-l4t-arm64-moss-transcribe-cpp-development alias: moss-transcribe-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | moss-transcribe.cpp is a C++/ggml port of OpenMOSS MOSS-Transcribe-Diarize, an end-to-end audio understanding model. It does joint long-form transcription, speaker diarization and timestamping in a single pass, emitting a speaker-labelled, time-aligned transcript, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan, Apple Metal and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/moss-transcribe.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-moss-transcribe-cpp default: cpu-moss-transcribe-cpp intel: intel-sycl-f16-moss-transcribe-cpp metal: metal-moss-transcribe-cpp nvidia: cuda12-moss-transcribe-cpp nvidia-cuda-12: cuda12-moss-transcribe-cpp nvidia-cuda-13: cuda13-moss-transcribe-cpp nvidia-l4t: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-transcribe-cpp vulkan: vulkan-moss-transcribe-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-moss-transcribe-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-arm64-moss-transcribe-cpp - name: cuda13-nvidia-l4t-arm64-moss-transcribe-cpp alias: moss-transcribe-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | moss-transcribe.cpp is a C++/ggml port of OpenMOSS MOSS-Transcribe-Diarize, an end-to-end audio understanding model. It does joint long-form transcription, speaker diarization and timestamping in a single pass, emitting a speaker-labelled, time-aligned transcript, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan, Apple Metal and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/moss-transcribe.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-moss-transcribe-cpp default: cpu-moss-transcribe-cpp intel: intel-sycl-f16-moss-transcribe-cpp metal: metal-moss-transcribe-cpp nvidia: cuda12-moss-transcribe-cpp nvidia-cuda-12: cuda12-moss-transcribe-cpp nvidia-cuda-13: cuda13-moss-transcribe-cpp nvidia-l4t: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-transcribe-cpp vulkan: vulkan-moss-transcribe-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-moss-transcribe-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-moss-transcribe-cpp - name: cuda13-nvidia-l4t-arm64-moss-transcribe-cpp-development alias: moss-transcribe-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | moss-transcribe.cpp is a C++/ggml port of OpenMOSS MOSS-Transcribe-Diarize, an end-to-end audio understanding model. It does joint long-form transcription, speaker diarization and timestamping in a single pass, emitting a speaker-labelled, time-aligned transcript, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan, Apple Metal and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/moss-transcribe.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-moss-transcribe-cpp default: cpu-moss-transcribe-cpp intel: intel-sycl-f16-moss-transcribe-cpp metal: metal-moss-transcribe-cpp nvidia: cuda12-moss-transcribe-cpp nvidia-cuda-12: cuda12-moss-transcribe-cpp nvidia-cuda-13: cuda13-moss-transcribe-cpp nvidia-l4t: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-transcribe-cpp vulkan: vulkan-moss-transcribe-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-moss-transcribe-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-moss-transcribe-cpp - name: cpu-moss-transcribe-cpp alias: moss-transcribe-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | moss-transcribe.cpp is a C++/ggml port of OpenMOSS MOSS-Transcribe-Diarize, an end-to-end audio understanding model. It does joint long-form transcription, speaker diarization and timestamping in a single pass, emitting a speaker-labelled, time-aligned transcript, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan, Apple Metal and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/moss-transcribe.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-moss-transcribe-cpp default: cpu-moss-transcribe-cpp intel: intel-sycl-f16-moss-transcribe-cpp metal: metal-moss-transcribe-cpp nvidia: cuda12-moss-transcribe-cpp nvidia-cuda-12: cuda12-moss-transcribe-cpp nvidia-cuda-13: cuda13-moss-transcribe-cpp nvidia-l4t: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-transcribe-cpp vulkan: vulkan-moss-transcribe-cpp uri: quay.io/go-skynet/local-ai-backends:latest-cpu-moss-transcribe-cpp mirrors: - localai/localai-backends:latest-cpu-moss-transcribe-cpp - name: cpu-moss-transcribe-cpp-development alias: moss-transcribe-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | moss-transcribe.cpp is a C++/ggml port of OpenMOSS MOSS-Transcribe-Diarize, an end-to-end audio understanding model. It does joint long-form transcription, speaker diarization and timestamping in a single pass, emitting a speaker-labelled, time-aligned transcript, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan, Apple Metal and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/moss-transcribe.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-moss-transcribe-cpp default: cpu-moss-transcribe-cpp intel: intel-sycl-f16-moss-transcribe-cpp metal: metal-moss-transcribe-cpp nvidia: cuda12-moss-transcribe-cpp nvidia-cuda-12: cuda12-moss-transcribe-cpp nvidia-cuda-13: cuda13-moss-transcribe-cpp nvidia-l4t: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-transcribe-cpp vulkan: vulkan-moss-transcribe-cpp uri: quay.io/go-skynet/local-ai-backends:master-cpu-moss-transcribe-cpp mirrors: - localai/localai-backends:master-cpu-moss-transcribe-cpp - name: metal-moss-transcribe-cpp alias: moss-transcribe-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | moss-transcribe.cpp is a C++/ggml port of OpenMOSS MOSS-Transcribe-Diarize, an end-to-end audio understanding model. It does joint long-form transcription, speaker diarization and timestamping in a single pass, emitting a speaker-labelled, time-aligned transcript, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan, Apple Metal and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/moss-transcribe.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-moss-transcribe-cpp default: cpu-moss-transcribe-cpp intel: intel-sycl-f16-moss-transcribe-cpp metal: metal-moss-transcribe-cpp nvidia: cuda12-moss-transcribe-cpp nvidia-cuda-12: cuda12-moss-transcribe-cpp nvidia-cuda-13: cuda13-moss-transcribe-cpp nvidia-l4t: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-transcribe-cpp vulkan: vulkan-moss-transcribe-cpp uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-moss-transcribe-cpp mirrors: - localai/localai-backends:latest-metal-darwin-arm64-moss-transcribe-cpp - name: metal-moss-transcribe-cpp-development alias: moss-transcribe-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | moss-transcribe.cpp is a C++/ggml port of OpenMOSS MOSS-Transcribe-Diarize, an end-to-end audio understanding model. It does joint long-form transcription, speaker diarization and timestamping in a single pass, emitting a speaker-labelled, time-aligned transcript, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan, Apple Metal and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/moss-transcribe.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-moss-transcribe-cpp default: cpu-moss-transcribe-cpp intel: intel-sycl-f16-moss-transcribe-cpp metal: metal-moss-transcribe-cpp nvidia: cuda12-moss-transcribe-cpp nvidia-cuda-12: cuda12-moss-transcribe-cpp nvidia-cuda-13: cuda13-moss-transcribe-cpp nvidia-l4t: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-transcribe-cpp vulkan: vulkan-moss-transcribe-cpp uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-moss-transcribe-cpp mirrors: - localai/localai-backends:master-metal-darwin-arm64-moss-transcribe-cpp - name: cuda12-moss-transcribe-cpp alias: moss-transcribe-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | moss-transcribe.cpp is a C++/ggml port of OpenMOSS MOSS-Transcribe-Diarize, an end-to-end audio understanding model. It does joint long-form transcription, speaker diarization and timestamping in a single pass, emitting a speaker-labelled, time-aligned transcript, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan, Apple Metal and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/moss-transcribe.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-moss-transcribe-cpp default: cpu-moss-transcribe-cpp intel: intel-sycl-f16-moss-transcribe-cpp metal: metal-moss-transcribe-cpp nvidia: cuda12-moss-transcribe-cpp nvidia-cuda-12: cuda12-moss-transcribe-cpp nvidia-cuda-13: cuda13-moss-transcribe-cpp nvidia-l4t: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-transcribe-cpp vulkan: vulkan-moss-transcribe-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-moss-transcribe-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-moss-transcribe-cpp - name: cuda12-moss-transcribe-cpp-development alias: moss-transcribe-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | moss-transcribe.cpp is a C++/ggml port of OpenMOSS MOSS-Transcribe-Diarize, an end-to-end audio understanding model. It does joint long-form transcription, speaker diarization and timestamping in a single pass, emitting a speaker-labelled, time-aligned transcript, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan, Apple Metal and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/moss-transcribe.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-moss-transcribe-cpp default: cpu-moss-transcribe-cpp intel: intel-sycl-f16-moss-transcribe-cpp metal: metal-moss-transcribe-cpp nvidia: cuda12-moss-transcribe-cpp nvidia-cuda-12: cuda12-moss-transcribe-cpp nvidia-cuda-13: cuda13-moss-transcribe-cpp nvidia-l4t: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-transcribe-cpp vulkan: vulkan-moss-transcribe-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-moss-transcribe-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-moss-transcribe-cpp - name: rocm-moss-transcribe-cpp alias: moss-transcribe-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | moss-transcribe.cpp is a C++/ggml port of OpenMOSS MOSS-Transcribe-Diarize, an end-to-end audio understanding model. It does joint long-form transcription, speaker diarization and timestamping in a single pass, emitting a speaker-labelled, time-aligned transcript, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan, Apple Metal and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/moss-transcribe.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-moss-transcribe-cpp default: cpu-moss-transcribe-cpp intel: intel-sycl-f16-moss-transcribe-cpp metal: metal-moss-transcribe-cpp nvidia: cuda12-moss-transcribe-cpp nvidia-cuda-12: cuda12-moss-transcribe-cpp nvidia-cuda-13: cuda13-moss-transcribe-cpp nvidia-l4t: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-transcribe-cpp vulkan: vulkan-moss-transcribe-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-moss-transcribe-cpp mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-moss-transcribe-cpp - name: rocm-moss-transcribe-cpp-development alias: moss-transcribe-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | moss-transcribe.cpp is a C++/ggml port of OpenMOSS MOSS-Transcribe-Diarize, an end-to-end audio understanding model. It does joint long-form transcription, speaker diarization and timestamping in a single pass, emitting a speaker-labelled, time-aligned transcript, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan, Apple Metal and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/moss-transcribe.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-moss-transcribe-cpp default: cpu-moss-transcribe-cpp intel: intel-sycl-f16-moss-transcribe-cpp metal: metal-moss-transcribe-cpp nvidia: cuda12-moss-transcribe-cpp nvidia-cuda-12: cuda12-moss-transcribe-cpp nvidia-cuda-13: cuda13-moss-transcribe-cpp nvidia-l4t: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-transcribe-cpp vulkan: vulkan-moss-transcribe-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-moss-transcribe-cpp mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-moss-transcribe-cpp - name: intel-sycl-f32-moss-transcribe-cpp alias: moss-transcribe-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | moss-transcribe.cpp is a C++/ggml port of OpenMOSS MOSS-Transcribe-Diarize, an end-to-end audio understanding model. It does joint long-form transcription, speaker diarization and timestamping in a single pass, emitting a speaker-labelled, time-aligned transcript, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan, Apple Metal and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/moss-transcribe.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-moss-transcribe-cpp default: cpu-moss-transcribe-cpp intel: intel-sycl-f16-moss-transcribe-cpp metal: metal-moss-transcribe-cpp nvidia: cuda12-moss-transcribe-cpp nvidia-cuda-12: cuda12-moss-transcribe-cpp nvidia-cuda-13: cuda13-moss-transcribe-cpp nvidia-l4t: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-transcribe-cpp vulkan: vulkan-moss-transcribe-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-moss-transcribe-cpp mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f32-moss-transcribe-cpp - name: intel-sycl-f32-moss-transcribe-cpp-development alias: moss-transcribe-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | moss-transcribe.cpp is a C++/ggml port of OpenMOSS MOSS-Transcribe-Diarize, an end-to-end audio understanding model. It does joint long-form transcription, speaker diarization and timestamping in a single pass, emitting a speaker-labelled, time-aligned transcript, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan, Apple Metal and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/moss-transcribe.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-moss-transcribe-cpp default: cpu-moss-transcribe-cpp intel: intel-sycl-f16-moss-transcribe-cpp metal: metal-moss-transcribe-cpp nvidia: cuda12-moss-transcribe-cpp nvidia-cuda-12: cuda12-moss-transcribe-cpp nvidia-cuda-13: cuda13-moss-transcribe-cpp nvidia-l4t: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-transcribe-cpp vulkan: vulkan-moss-transcribe-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-moss-transcribe-cpp mirrors: - localai/localai-backends:master-gpu-intel-sycl-f32-moss-transcribe-cpp - name: intel-sycl-f16-moss-transcribe-cpp alias: moss-transcribe-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | moss-transcribe.cpp is a C++/ggml port of OpenMOSS MOSS-Transcribe-Diarize, an end-to-end audio understanding model. It does joint long-form transcription, speaker diarization and timestamping in a single pass, emitting a speaker-labelled, time-aligned transcript, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan, Apple Metal and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/moss-transcribe.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-moss-transcribe-cpp default: cpu-moss-transcribe-cpp intel: intel-sycl-f16-moss-transcribe-cpp metal: metal-moss-transcribe-cpp nvidia: cuda12-moss-transcribe-cpp nvidia-cuda-12: cuda12-moss-transcribe-cpp nvidia-cuda-13: cuda13-moss-transcribe-cpp nvidia-l4t: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-transcribe-cpp vulkan: vulkan-moss-transcribe-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-moss-transcribe-cpp mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f16-moss-transcribe-cpp - name: intel-sycl-f16-moss-transcribe-cpp-development alias: moss-transcribe-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | moss-transcribe.cpp is a C++/ggml port of OpenMOSS MOSS-Transcribe-Diarize, an end-to-end audio understanding model. It does joint long-form transcription, speaker diarization and timestamping in a single pass, emitting a speaker-labelled, time-aligned transcript, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan, Apple Metal and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/moss-transcribe.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-moss-transcribe-cpp default: cpu-moss-transcribe-cpp intel: intel-sycl-f16-moss-transcribe-cpp metal: metal-moss-transcribe-cpp nvidia: cuda12-moss-transcribe-cpp nvidia-cuda-12: cuda12-moss-transcribe-cpp nvidia-cuda-13: cuda13-moss-transcribe-cpp nvidia-l4t: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-transcribe-cpp vulkan: vulkan-moss-transcribe-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-moss-transcribe-cpp mirrors: - localai/localai-backends:master-gpu-intel-sycl-f16-moss-transcribe-cpp - name: vulkan-moss-transcribe-cpp alias: moss-transcribe-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | moss-transcribe.cpp is a C++/ggml port of OpenMOSS MOSS-Transcribe-Diarize, an end-to-end audio understanding model. It does joint long-form transcription, speaker diarization and timestamping in a single pass, emitting a speaker-labelled, time-aligned transcript, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan, Apple Metal and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/moss-transcribe.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-moss-transcribe-cpp default: cpu-moss-transcribe-cpp intel: intel-sycl-f16-moss-transcribe-cpp metal: metal-moss-transcribe-cpp nvidia: cuda12-moss-transcribe-cpp nvidia-cuda-12: cuda12-moss-transcribe-cpp nvidia-cuda-13: cuda13-moss-transcribe-cpp nvidia-l4t: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-transcribe-cpp vulkan: vulkan-moss-transcribe-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-moss-transcribe-cpp mirrors: - localai/localai-backends:latest-gpu-vulkan-moss-transcribe-cpp - name: vulkan-moss-transcribe-cpp-development alias: moss-transcribe-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | moss-transcribe.cpp is a C++/ggml port of OpenMOSS MOSS-Transcribe-Diarize, an end-to-end audio understanding model. It does joint long-form transcription, speaker diarization and timestamping in a single pass, emitting a speaker-labelled, time-aligned transcript, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan, Apple Metal and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/moss-transcribe.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-moss-transcribe-cpp default: cpu-moss-transcribe-cpp intel: intel-sycl-f16-moss-transcribe-cpp metal: metal-moss-transcribe-cpp nvidia: cuda12-moss-transcribe-cpp nvidia-cuda-12: cuda12-moss-transcribe-cpp nvidia-cuda-13: cuda13-moss-transcribe-cpp nvidia-l4t: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-transcribe-cpp vulkan: vulkan-moss-transcribe-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-moss-transcribe-cpp mirrors: - localai/localai-backends:master-gpu-vulkan-moss-transcribe-cpp - name: cuda13-moss-transcribe-cpp alias: moss-transcribe-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | moss-transcribe.cpp is a C++/ggml port of OpenMOSS MOSS-Transcribe-Diarize, an end-to-end audio understanding model. It does joint long-form transcription, speaker diarization and timestamping in a single pass, emitting a speaker-labelled, time-aligned transcript, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan, Apple Metal and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/moss-transcribe.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-moss-transcribe-cpp default: cpu-moss-transcribe-cpp intel: intel-sycl-f16-moss-transcribe-cpp metal: metal-moss-transcribe-cpp nvidia: cuda12-moss-transcribe-cpp nvidia-cuda-12: cuda12-moss-transcribe-cpp nvidia-cuda-13: cuda13-moss-transcribe-cpp nvidia-l4t: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-transcribe-cpp vulkan: vulkan-moss-transcribe-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-moss-transcribe-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-moss-transcribe-cpp - name: cuda13-moss-transcribe-cpp-development alias: moss-transcribe-cpp license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | moss-transcribe.cpp is a C++/ggml port of OpenMOSS MOSS-Transcribe-Diarize, an end-to-end audio understanding model. It does joint long-form transcription, speaker diarization and timestamping in a single pass, emitting a speaker-labelled, time-aligned transcript, and runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan, Apple Metal and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/moss-transcribe.cpp tags: - audio-transcription - CPU - GPU - CUDA - HIP capabilities: amd: rocm-moss-transcribe-cpp default: cpu-moss-transcribe-cpp intel: intel-sycl-f16-moss-transcribe-cpp metal: metal-moss-transcribe-cpp nvidia: cuda12-moss-transcribe-cpp nvidia-cuda-12: cuda12-moss-transcribe-cpp nvidia-cuda-13: cuda13-moss-transcribe-cpp nvidia-l4t: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-transcribe-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-transcribe-cpp vulkan: vulkan-moss-transcribe-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-moss-transcribe-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-moss-transcribe-cpp - name: ced-development alias: ced license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | CED sound-event classification / audio tagging (527-class AudioSet). ced.cpp is a C++/ggml port that performs audio tagging over the AudioSet taxonomy, exposed through the SoundDetection gRPC rpc and the /v1/audio/classification REST endpoint. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/ced.cpp tags: - audio-classification - CPU - GPU - CUDA - HIP capabilities: amd: rocm-ced-development default: cpu-ced-development intel: intel-sycl-f16-ced-development metal: metal-ced-development nvidia: cuda12-ced-development nvidia-cuda-12: cuda12-ced-development nvidia-cuda-13: cuda13-ced-development nvidia-l4t: nvidia-l4t-arm64-ced-development nvidia-l4t-cuda-12: nvidia-l4t-arm64-ced-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ced-development vulkan: vulkan-ced-development - name: nvidia-l4t-arm64-ced alias: ced license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | CED sound-event classification / audio tagging (527-class AudioSet). ced.cpp is a C++/ggml port that performs audio tagging over the AudioSet taxonomy, exposed through the SoundDetection gRPC rpc and the /v1/audio/classification REST endpoint. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/ced.cpp tags: - audio-classification - CPU - GPU - CUDA - HIP capabilities: amd: rocm-ced default: cpu-ced intel: intel-sycl-f16-ced metal: metal-ced nvidia: cuda12-ced nvidia-cuda-12: cuda12-ced nvidia-cuda-13: cuda13-ced nvidia-l4t: nvidia-l4t-arm64-ced nvidia-l4t-cuda-12: nvidia-l4t-arm64-ced nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ced vulkan: vulkan-ced uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-ced mirrors: - localai/localai-backends:latest-nvidia-l4t-arm64-ced - name: nvidia-l4t-arm64-ced-development alias: ced license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | CED sound-event classification / audio tagging (527-class AudioSet). ced.cpp is a C++/ggml port that performs audio tagging over the AudioSet taxonomy, exposed through the SoundDetection gRPC rpc and the /v1/audio/classification REST endpoint. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/ced.cpp tags: - audio-classification - CPU - GPU - CUDA - HIP capabilities: amd: rocm-ced default: cpu-ced intel: intel-sycl-f16-ced metal: metal-ced nvidia: cuda12-ced nvidia-cuda-12: cuda12-ced nvidia-cuda-13: cuda13-ced nvidia-l4t: nvidia-l4t-arm64-ced nvidia-l4t-cuda-12: nvidia-l4t-arm64-ced nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ced vulkan: vulkan-ced uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-ced mirrors: - localai/localai-backends:master-nvidia-l4t-arm64-ced - name: cuda13-nvidia-l4t-arm64-ced alias: ced license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | CED sound-event classification / audio tagging (527-class AudioSet). ced.cpp is a C++/ggml port that performs audio tagging over the AudioSet taxonomy, exposed through the SoundDetection gRPC rpc and the /v1/audio/classification REST endpoint. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/ced.cpp tags: - audio-classification - CPU - GPU - CUDA - HIP capabilities: amd: rocm-ced default: cpu-ced intel: intel-sycl-f16-ced metal: metal-ced nvidia: cuda12-ced nvidia-cuda-12: cuda12-ced nvidia-cuda-13: cuda13-ced nvidia-l4t: nvidia-l4t-arm64-ced nvidia-l4t-cuda-12: nvidia-l4t-arm64-ced nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ced vulkan: vulkan-ced uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-ced mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-ced - name: cuda13-nvidia-l4t-arm64-ced-development alias: ced license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | CED sound-event classification / audio tagging (527-class AudioSet). ced.cpp is a C++/ggml port that performs audio tagging over the AudioSet taxonomy, exposed through the SoundDetection gRPC rpc and the /v1/audio/classification REST endpoint. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/ced.cpp tags: - audio-classification - CPU - GPU - CUDA - HIP capabilities: amd: rocm-ced default: cpu-ced intel: intel-sycl-f16-ced metal: metal-ced nvidia: cuda12-ced nvidia-cuda-12: cuda12-ced nvidia-cuda-13: cuda13-ced nvidia-l4t: nvidia-l4t-arm64-ced nvidia-l4t-cuda-12: nvidia-l4t-arm64-ced nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ced vulkan: vulkan-ced uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-ced mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-ced - name: cpu-ced alias: ced license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | CED sound-event classification / audio tagging (527-class AudioSet). ced.cpp is a C++/ggml port that performs audio tagging over the AudioSet taxonomy, exposed through the SoundDetection gRPC rpc and the /v1/audio/classification REST endpoint. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/ced.cpp tags: - audio-classification - CPU - GPU - CUDA - HIP capabilities: amd: rocm-ced default: cpu-ced intel: intel-sycl-f16-ced metal: metal-ced nvidia: cuda12-ced nvidia-cuda-12: cuda12-ced nvidia-cuda-13: cuda13-ced nvidia-l4t: nvidia-l4t-arm64-ced nvidia-l4t-cuda-12: nvidia-l4t-arm64-ced nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ced vulkan: vulkan-ced uri: quay.io/go-skynet/local-ai-backends:latest-cpu-ced mirrors: - localai/localai-backends:latest-cpu-ced - name: cpu-ced-development alias: ced license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | CED sound-event classification / audio tagging (527-class AudioSet). ced.cpp is a C++/ggml port that performs audio tagging over the AudioSet taxonomy, exposed through the SoundDetection gRPC rpc and the /v1/audio/classification REST endpoint. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/ced.cpp tags: - audio-classification - CPU - GPU - CUDA - HIP capabilities: amd: rocm-ced default: cpu-ced intel: intel-sycl-f16-ced metal: metal-ced nvidia: cuda12-ced nvidia-cuda-12: cuda12-ced nvidia-cuda-13: cuda13-ced nvidia-l4t: nvidia-l4t-arm64-ced nvidia-l4t-cuda-12: nvidia-l4t-arm64-ced nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ced vulkan: vulkan-ced uri: quay.io/go-skynet/local-ai-backends:master-cpu-ced mirrors: - localai/localai-backends:master-cpu-ced - name: metal-ced alias: ced license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | CED sound-event classification / audio tagging (527-class AudioSet). ced.cpp is a C++/ggml port that performs audio tagging over the AudioSet taxonomy, exposed through the SoundDetection gRPC rpc and the /v1/audio/classification REST endpoint. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/ced.cpp tags: - audio-classification - CPU - GPU - CUDA - HIP capabilities: amd: rocm-ced default: cpu-ced intel: intel-sycl-f16-ced metal: metal-ced nvidia: cuda12-ced nvidia-cuda-12: cuda12-ced nvidia-cuda-13: cuda13-ced nvidia-l4t: nvidia-l4t-arm64-ced nvidia-l4t-cuda-12: nvidia-l4t-arm64-ced nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ced vulkan: vulkan-ced uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-ced mirrors: - localai/localai-backends:latest-metal-darwin-arm64-ced - name: metal-ced-development alias: ced license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | CED sound-event classification / audio tagging (527-class AudioSet). ced.cpp is a C++/ggml port that performs audio tagging over the AudioSet taxonomy, exposed through the SoundDetection gRPC rpc and the /v1/audio/classification REST endpoint. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/ced.cpp tags: - audio-classification - CPU - GPU - CUDA - HIP capabilities: amd: rocm-ced default: cpu-ced intel: intel-sycl-f16-ced metal: metal-ced nvidia: cuda12-ced nvidia-cuda-12: cuda12-ced nvidia-cuda-13: cuda13-ced nvidia-l4t: nvidia-l4t-arm64-ced nvidia-l4t-cuda-12: nvidia-l4t-arm64-ced nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ced vulkan: vulkan-ced uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-ced mirrors: - localai/localai-backends:master-metal-darwin-arm64-ced - name: cuda12-ced alias: ced license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | CED sound-event classification / audio tagging (527-class AudioSet). ced.cpp is a C++/ggml port that performs audio tagging over the AudioSet taxonomy, exposed through the SoundDetection gRPC rpc and the /v1/audio/classification REST endpoint. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/ced.cpp tags: - audio-classification - CPU - GPU - CUDA - HIP capabilities: amd: rocm-ced default: cpu-ced intel: intel-sycl-f16-ced metal: metal-ced nvidia: cuda12-ced nvidia-cuda-12: cuda12-ced nvidia-cuda-13: cuda13-ced nvidia-l4t: nvidia-l4t-arm64-ced nvidia-l4t-cuda-12: nvidia-l4t-arm64-ced nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ced vulkan: vulkan-ced uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-ced mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-ced - name: cuda12-ced-development alias: ced license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | CED sound-event classification / audio tagging (527-class AudioSet). ced.cpp is a C++/ggml port that performs audio tagging over the AudioSet taxonomy, exposed through the SoundDetection gRPC rpc and the /v1/audio/classification REST endpoint. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/ced.cpp tags: - audio-classification - CPU - GPU - CUDA - HIP capabilities: amd: rocm-ced default: cpu-ced intel: intel-sycl-f16-ced metal: metal-ced nvidia: cuda12-ced nvidia-cuda-12: cuda12-ced nvidia-cuda-13: cuda13-ced nvidia-l4t: nvidia-l4t-arm64-ced nvidia-l4t-cuda-12: nvidia-l4t-arm64-ced nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ced vulkan: vulkan-ced uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-ced mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-ced - name: rocm-ced alias: ced license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | CED sound-event classification / audio tagging (527-class AudioSet). ced.cpp is a C++/ggml port that performs audio tagging over the AudioSet taxonomy, exposed through the SoundDetection gRPC rpc and the /v1/audio/classification REST endpoint. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/ced.cpp tags: - audio-classification - CPU - GPU - CUDA - HIP capabilities: amd: rocm-ced default: cpu-ced intel: intel-sycl-f16-ced metal: metal-ced nvidia: cuda12-ced nvidia-cuda-12: cuda12-ced nvidia-cuda-13: cuda13-ced nvidia-l4t: nvidia-l4t-arm64-ced nvidia-l4t-cuda-12: nvidia-l4t-arm64-ced nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ced vulkan: vulkan-ced uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-ced mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-ced - name: rocm-ced-development alias: ced license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | CED sound-event classification / audio tagging (527-class AudioSet). ced.cpp is a C++/ggml port that performs audio tagging over the AudioSet taxonomy, exposed through the SoundDetection gRPC rpc and the /v1/audio/classification REST endpoint. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/ced.cpp tags: - audio-classification - CPU - GPU - CUDA - HIP capabilities: amd: rocm-ced default: cpu-ced intel: intel-sycl-f16-ced metal: metal-ced nvidia: cuda12-ced nvidia-cuda-12: cuda12-ced nvidia-cuda-13: cuda13-ced nvidia-l4t: nvidia-l4t-arm64-ced nvidia-l4t-cuda-12: nvidia-l4t-arm64-ced nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ced vulkan: vulkan-ced uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-ced mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-ced - name: intel-sycl-f32-ced alias: ced license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | CED sound-event classification / audio tagging (527-class AudioSet). ced.cpp is a C++/ggml port that performs audio tagging over the AudioSet taxonomy, exposed through the SoundDetection gRPC rpc and the /v1/audio/classification REST endpoint. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/ced.cpp tags: - audio-classification - CPU - GPU - CUDA - HIP capabilities: amd: rocm-ced default: cpu-ced intel: intel-sycl-f16-ced metal: metal-ced nvidia: cuda12-ced nvidia-cuda-12: cuda12-ced nvidia-cuda-13: cuda13-ced nvidia-l4t: nvidia-l4t-arm64-ced nvidia-l4t-cuda-12: nvidia-l4t-arm64-ced nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ced vulkan: vulkan-ced uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-ced mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f32-ced - name: intel-sycl-f32-ced-development alias: ced license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | CED sound-event classification / audio tagging (527-class AudioSet). ced.cpp is a C++/ggml port that performs audio tagging over the AudioSet taxonomy, exposed through the SoundDetection gRPC rpc and the /v1/audio/classification REST endpoint. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/ced.cpp tags: - audio-classification - CPU - GPU - CUDA - HIP capabilities: amd: rocm-ced default: cpu-ced intel: intel-sycl-f16-ced metal: metal-ced nvidia: cuda12-ced nvidia-cuda-12: cuda12-ced nvidia-cuda-13: cuda13-ced nvidia-l4t: nvidia-l4t-arm64-ced nvidia-l4t-cuda-12: nvidia-l4t-arm64-ced nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ced vulkan: vulkan-ced uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-ced mirrors: - localai/localai-backends:master-gpu-intel-sycl-f32-ced - name: intel-sycl-f16-ced alias: ced license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | CED sound-event classification / audio tagging (527-class AudioSet). ced.cpp is a C++/ggml port that performs audio tagging over the AudioSet taxonomy, exposed through the SoundDetection gRPC rpc and the /v1/audio/classification REST endpoint. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/ced.cpp tags: - audio-classification - CPU - GPU - CUDA - HIP capabilities: amd: rocm-ced default: cpu-ced intel: intel-sycl-f16-ced metal: metal-ced nvidia: cuda12-ced nvidia-cuda-12: cuda12-ced nvidia-cuda-13: cuda13-ced nvidia-l4t: nvidia-l4t-arm64-ced nvidia-l4t-cuda-12: nvidia-l4t-arm64-ced nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ced vulkan: vulkan-ced uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-ced mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f16-ced - name: intel-sycl-f16-ced-development alias: ced license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | CED sound-event classification / audio tagging (527-class AudioSet). ced.cpp is a C++/ggml port that performs audio tagging over the AudioSet taxonomy, exposed through the SoundDetection gRPC rpc and the /v1/audio/classification REST endpoint. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/ced.cpp tags: - audio-classification - CPU - GPU - CUDA - HIP capabilities: amd: rocm-ced default: cpu-ced intel: intel-sycl-f16-ced metal: metal-ced nvidia: cuda12-ced nvidia-cuda-12: cuda12-ced nvidia-cuda-13: cuda13-ced nvidia-l4t: nvidia-l4t-arm64-ced nvidia-l4t-cuda-12: nvidia-l4t-arm64-ced nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ced vulkan: vulkan-ced uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-ced mirrors: - localai/localai-backends:master-gpu-intel-sycl-f16-ced - name: vulkan-ced alias: ced license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | CED sound-event classification / audio tagging (527-class AudioSet). ced.cpp is a C++/ggml port that performs audio tagging over the AudioSet taxonomy, exposed through the SoundDetection gRPC rpc and the /v1/audio/classification REST endpoint. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/ced.cpp tags: - audio-classification - CPU - GPU - CUDA - HIP capabilities: amd: rocm-ced default: cpu-ced intel: intel-sycl-f16-ced metal: metal-ced nvidia: cuda12-ced nvidia-cuda-12: cuda12-ced nvidia-cuda-13: cuda13-ced nvidia-l4t: nvidia-l4t-arm64-ced nvidia-l4t-cuda-12: nvidia-l4t-arm64-ced nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ced vulkan: vulkan-ced uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-ced mirrors: - localai/localai-backends:latest-gpu-vulkan-ced - name: vulkan-ced-development alias: ced license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | CED sound-event classification / audio tagging (527-class AudioSet). ced.cpp is a C++/ggml port that performs audio tagging over the AudioSet taxonomy, exposed through the SoundDetection gRPC rpc and the /v1/audio/classification REST endpoint. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/ced.cpp tags: - audio-classification - CPU - GPU - CUDA - HIP capabilities: amd: rocm-ced default: cpu-ced intel: intel-sycl-f16-ced metal: metal-ced nvidia: cuda12-ced nvidia-cuda-12: cuda12-ced nvidia-cuda-13: cuda13-ced nvidia-l4t: nvidia-l4t-arm64-ced nvidia-l4t-cuda-12: nvidia-l4t-arm64-ced nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ced vulkan: vulkan-ced uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-ced mirrors: - localai/localai-backends:master-gpu-vulkan-ced - name: cuda13-ced alias: ced license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | CED sound-event classification / audio tagging (527-class AudioSet). ced.cpp is a C++/ggml port that performs audio tagging over the AudioSet taxonomy, exposed through the SoundDetection gRPC rpc and the /v1/audio/classification REST endpoint. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/ced.cpp tags: - audio-classification - CPU - GPU - CUDA - HIP capabilities: amd: rocm-ced default: cpu-ced intel: intel-sycl-f16-ced metal: metal-ced nvidia: cuda12-ced nvidia-cuda-12: cuda12-ced nvidia-cuda-13: cuda13-ced nvidia-l4t: nvidia-l4t-arm64-ced nvidia-l4t-cuda-12: nvidia-l4t-arm64-ced nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ced vulkan: vulkan-ced uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-ced mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-ced - name: cuda13-ced-development alias: ced license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | CED sound-event classification / audio tagging (527-class AudioSet). ced.cpp is a C++/ggml port that performs audio tagging over the AudioSet taxonomy, exposed through the SoundDetection gRPC rpc and the /v1/audio/classification REST endpoint. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/ced.cpp tags: - audio-classification - CPU - GPU - CUDA - HIP capabilities: amd: rocm-ced default: cpu-ced intel: intel-sycl-f16-ced metal: metal-ced nvidia: cuda12-ced nvidia-cuda-12: cuda12-ced nvidia-cuda-13: cuda13-ced nvidia-l4t: nvidia-l4t-arm64-ced nvidia-l4t-cuda-12: nvidia-l4t-arm64-ced nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-ced vulkan: vulkan-ced uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-ced mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-ced - name: voice-detect-development alias: voice-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | voice-detect speaker recognition and voice analysis. voice-detect.cpp is a C++/ggml engine that produces L2-normalised speaker embeddings (ECAPA-TDNN, WeSpeaker ResNet34, 3D-Speaker ERes2Net, CAM++) for voice verification and 1:N identification, plus a wav2vec2 age / gender / emotion analysis head. It replaces the Python speaker-recognition backend and is exposed through the Voice* gRPC rpcs and the /v1/voice/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/voice-detect.cpp tags: - voice-recognition - speaker-verification - speaker-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-voice-detect-development default: cpu-voice-detect-development intel: intel-sycl-f16-voice-detect-development metal: metal-voice-detect-development nvidia: cuda12-voice-detect-development nvidia-cuda-12: cuda12-voice-detect-development nvidia-cuda-13: cuda13-voice-detect-development nvidia-l4t: nvidia-l4t-arm64-voice-detect-development nvidia-l4t-cuda-12: nvidia-l4t-arm64-voice-detect-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-voice-detect-development vulkan: vulkan-voice-detect-development - name: nvidia-l4t-arm64-voice-detect alias: voice-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | voice-detect speaker recognition and voice analysis. voice-detect.cpp is a C++/ggml engine that produces L2-normalised speaker embeddings (ECAPA-TDNN, WeSpeaker ResNet34, 3D-Speaker ERes2Net, CAM++) for voice verification and 1:N identification, plus a wav2vec2 age / gender / emotion analysis head. It replaces the Python speaker-recognition backend and is exposed through the Voice* gRPC rpcs and the /v1/voice/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/voice-detect.cpp tags: - voice-recognition - speaker-verification - speaker-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-voice-detect default: cpu-voice-detect intel: intel-sycl-f16-voice-detect metal: metal-voice-detect nvidia: cuda12-voice-detect nvidia-cuda-12: cuda12-voice-detect nvidia-cuda-13: cuda13-voice-detect nvidia-l4t: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-voice-detect vulkan: vulkan-voice-detect uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-voice-detect mirrors: - localai/localai-backends:latest-nvidia-l4t-arm64-voice-detect - name: nvidia-l4t-arm64-voice-detect-development alias: voice-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | voice-detect speaker recognition and voice analysis. voice-detect.cpp is a C++/ggml engine that produces L2-normalised speaker embeddings (ECAPA-TDNN, WeSpeaker ResNet34, 3D-Speaker ERes2Net, CAM++) for voice verification and 1:N identification, plus a wav2vec2 age / gender / emotion analysis head. It replaces the Python speaker-recognition backend and is exposed through the Voice* gRPC rpcs and the /v1/voice/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/voice-detect.cpp tags: - voice-recognition - speaker-verification - speaker-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-voice-detect default: cpu-voice-detect intel: intel-sycl-f16-voice-detect metal: metal-voice-detect nvidia: cuda12-voice-detect nvidia-cuda-12: cuda12-voice-detect nvidia-cuda-13: cuda13-voice-detect nvidia-l4t: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-voice-detect vulkan: vulkan-voice-detect uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-voice-detect mirrors: - localai/localai-backends:master-nvidia-l4t-arm64-voice-detect - name: cuda13-nvidia-l4t-arm64-voice-detect alias: voice-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | voice-detect speaker recognition and voice analysis. voice-detect.cpp is a C++/ggml engine that produces L2-normalised speaker embeddings (ECAPA-TDNN, WeSpeaker ResNet34, 3D-Speaker ERes2Net, CAM++) for voice verification and 1:N identification, plus a wav2vec2 age / gender / emotion analysis head. It replaces the Python speaker-recognition backend and is exposed through the Voice* gRPC rpcs and the /v1/voice/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/voice-detect.cpp tags: - voice-recognition - speaker-verification - speaker-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-voice-detect default: cpu-voice-detect intel: intel-sycl-f16-voice-detect metal: metal-voice-detect nvidia: cuda12-voice-detect nvidia-cuda-12: cuda12-voice-detect nvidia-cuda-13: cuda13-voice-detect nvidia-l4t: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-voice-detect vulkan: vulkan-voice-detect uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-voice-detect mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-voice-detect - name: cuda13-nvidia-l4t-arm64-voice-detect-development alias: voice-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | voice-detect speaker recognition and voice analysis. voice-detect.cpp is a C++/ggml engine that produces L2-normalised speaker embeddings (ECAPA-TDNN, WeSpeaker ResNet34, 3D-Speaker ERes2Net, CAM++) for voice verification and 1:N identification, plus a wav2vec2 age / gender / emotion analysis head. It replaces the Python speaker-recognition backend and is exposed through the Voice* gRPC rpcs and the /v1/voice/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/voice-detect.cpp tags: - voice-recognition - speaker-verification - speaker-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-voice-detect default: cpu-voice-detect intel: intel-sycl-f16-voice-detect metal: metal-voice-detect nvidia: cuda12-voice-detect nvidia-cuda-12: cuda12-voice-detect nvidia-cuda-13: cuda13-voice-detect nvidia-l4t: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-voice-detect vulkan: vulkan-voice-detect uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-voice-detect mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-voice-detect - name: cpu-voice-detect alias: voice-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | voice-detect speaker recognition and voice analysis. voice-detect.cpp is a C++/ggml engine that produces L2-normalised speaker embeddings (ECAPA-TDNN, WeSpeaker ResNet34, 3D-Speaker ERes2Net, CAM++) for voice verification and 1:N identification, plus a wav2vec2 age / gender / emotion analysis head. It replaces the Python speaker-recognition backend and is exposed through the Voice* gRPC rpcs and the /v1/voice/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/voice-detect.cpp tags: - voice-recognition - speaker-verification - speaker-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-voice-detect default: cpu-voice-detect intel: intel-sycl-f16-voice-detect metal: metal-voice-detect nvidia: cuda12-voice-detect nvidia-cuda-12: cuda12-voice-detect nvidia-cuda-13: cuda13-voice-detect nvidia-l4t: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-voice-detect vulkan: vulkan-voice-detect uri: quay.io/go-skynet/local-ai-backends:latest-cpu-voice-detect mirrors: - localai/localai-backends:latest-cpu-voice-detect - name: cpu-voice-detect-development alias: voice-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | voice-detect speaker recognition and voice analysis. voice-detect.cpp is a C++/ggml engine that produces L2-normalised speaker embeddings (ECAPA-TDNN, WeSpeaker ResNet34, 3D-Speaker ERes2Net, CAM++) for voice verification and 1:N identification, plus a wav2vec2 age / gender / emotion analysis head. It replaces the Python speaker-recognition backend and is exposed through the Voice* gRPC rpcs and the /v1/voice/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/voice-detect.cpp tags: - voice-recognition - speaker-verification - speaker-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-voice-detect default: cpu-voice-detect intel: intel-sycl-f16-voice-detect metal: metal-voice-detect nvidia: cuda12-voice-detect nvidia-cuda-12: cuda12-voice-detect nvidia-cuda-13: cuda13-voice-detect nvidia-l4t: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-voice-detect vulkan: vulkan-voice-detect uri: quay.io/go-skynet/local-ai-backends:master-cpu-voice-detect mirrors: - localai/localai-backends:master-cpu-voice-detect - name: metal-voice-detect alias: voice-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | voice-detect speaker recognition and voice analysis. voice-detect.cpp is a C++/ggml engine that produces L2-normalised speaker embeddings (ECAPA-TDNN, WeSpeaker ResNet34, 3D-Speaker ERes2Net, CAM++) for voice verification and 1:N identification, plus a wav2vec2 age / gender / emotion analysis head. It replaces the Python speaker-recognition backend and is exposed through the Voice* gRPC rpcs and the /v1/voice/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/voice-detect.cpp tags: - voice-recognition - speaker-verification - speaker-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-voice-detect default: cpu-voice-detect intel: intel-sycl-f16-voice-detect metal: metal-voice-detect nvidia: cuda12-voice-detect nvidia-cuda-12: cuda12-voice-detect nvidia-cuda-13: cuda13-voice-detect nvidia-l4t: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-voice-detect vulkan: vulkan-voice-detect uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-voice-detect mirrors: - localai/localai-backends:latest-metal-darwin-arm64-voice-detect - name: metal-voice-detect-development alias: voice-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | voice-detect speaker recognition and voice analysis. voice-detect.cpp is a C++/ggml engine that produces L2-normalised speaker embeddings (ECAPA-TDNN, WeSpeaker ResNet34, 3D-Speaker ERes2Net, CAM++) for voice verification and 1:N identification, plus a wav2vec2 age / gender / emotion analysis head. It replaces the Python speaker-recognition backend and is exposed through the Voice* gRPC rpcs and the /v1/voice/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/voice-detect.cpp tags: - voice-recognition - speaker-verification - speaker-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-voice-detect default: cpu-voice-detect intel: intel-sycl-f16-voice-detect metal: metal-voice-detect nvidia: cuda12-voice-detect nvidia-cuda-12: cuda12-voice-detect nvidia-cuda-13: cuda13-voice-detect nvidia-l4t: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-voice-detect vulkan: vulkan-voice-detect uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-voice-detect mirrors: - localai/localai-backends:master-metal-darwin-arm64-voice-detect - name: cuda12-voice-detect alias: voice-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | voice-detect speaker recognition and voice analysis. voice-detect.cpp is a C++/ggml engine that produces L2-normalised speaker embeddings (ECAPA-TDNN, WeSpeaker ResNet34, 3D-Speaker ERes2Net, CAM++) for voice verification and 1:N identification, plus a wav2vec2 age / gender / emotion analysis head. It replaces the Python speaker-recognition backend and is exposed through the Voice* gRPC rpcs and the /v1/voice/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/voice-detect.cpp tags: - voice-recognition - speaker-verification - speaker-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-voice-detect default: cpu-voice-detect intel: intel-sycl-f16-voice-detect metal: metal-voice-detect nvidia: cuda12-voice-detect nvidia-cuda-12: cuda12-voice-detect nvidia-cuda-13: cuda13-voice-detect nvidia-l4t: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-voice-detect vulkan: vulkan-voice-detect uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-voice-detect mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-voice-detect - name: cuda12-voice-detect-development alias: voice-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | voice-detect speaker recognition and voice analysis. voice-detect.cpp is a C++/ggml engine that produces L2-normalised speaker embeddings (ECAPA-TDNN, WeSpeaker ResNet34, 3D-Speaker ERes2Net, CAM++) for voice verification and 1:N identification, plus a wav2vec2 age / gender / emotion analysis head. It replaces the Python speaker-recognition backend and is exposed through the Voice* gRPC rpcs and the /v1/voice/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/voice-detect.cpp tags: - voice-recognition - speaker-verification - speaker-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-voice-detect default: cpu-voice-detect intel: intel-sycl-f16-voice-detect metal: metal-voice-detect nvidia: cuda12-voice-detect nvidia-cuda-12: cuda12-voice-detect nvidia-cuda-13: cuda13-voice-detect nvidia-l4t: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-voice-detect vulkan: vulkan-voice-detect uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-voice-detect mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-voice-detect - name: rocm-voice-detect alias: voice-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | voice-detect speaker recognition and voice analysis. voice-detect.cpp is a C++/ggml engine that produces L2-normalised speaker embeddings (ECAPA-TDNN, WeSpeaker ResNet34, 3D-Speaker ERes2Net, CAM++) for voice verification and 1:N identification, plus a wav2vec2 age / gender / emotion analysis head. It replaces the Python speaker-recognition backend and is exposed through the Voice* gRPC rpcs and the /v1/voice/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/voice-detect.cpp tags: - voice-recognition - speaker-verification - speaker-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-voice-detect default: cpu-voice-detect intel: intel-sycl-f16-voice-detect metal: metal-voice-detect nvidia: cuda12-voice-detect nvidia-cuda-12: cuda12-voice-detect nvidia-cuda-13: cuda13-voice-detect nvidia-l4t: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-voice-detect vulkan: vulkan-voice-detect uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-voice-detect mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-voice-detect - name: rocm-voice-detect-development alias: voice-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | voice-detect speaker recognition and voice analysis. voice-detect.cpp is a C++/ggml engine that produces L2-normalised speaker embeddings (ECAPA-TDNN, WeSpeaker ResNet34, 3D-Speaker ERes2Net, CAM++) for voice verification and 1:N identification, plus a wav2vec2 age / gender / emotion analysis head. It replaces the Python speaker-recognition backend and is exposed through the Voice* gRPC rpcs and the /v1/voice/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/voice-detect.cpp tags: - voice-recognition - speaker-verification - speaker-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-voice-detect default: cpu-voice-detect intel: intel-sycl-f16-voice-detect metal: metal-voice-detect nvidia: cuda12-voice-detect nvidia-cuda-12: cuda12-voice-detect nvidia-cuda-13: cuda13-voice-detect nvidia-l4t: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-voice-detect vulkan: vulkan-voice-detect uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-voice-detect mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-voice-detect - name: intel-sycl-f32-voice-detect alias: voice-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | voice-detect speaker recognition and voice analysis. voice-detect.cpp is a C++/ggml engine that produces L2-normalised speaker embeddings (ECAPA-TDNN, WeSpeaker ResNet34, 3D-Speaker ERes2Net, CAM++) for voice verification and 1:N identification, plus a wav2vec2 age / gender / emotion analysis head. It replaces the Python speaker-recognition backend and is exposed through the Voice* gRPC rpcs and the /v1/voice/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/voice-detect.cpp tags: - voice-recognition - speaker-verification - speaker-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-voice-detect default: cpu-voice-detect intel: intel-sycl-f16-voice-detect metal: metal-voice-detect nvidia: cuda12-voice-detect nvidia-cuda-12: cuda12-voice-detect nvidia-cuda-13: cuda13-voice-detect nvidia-l4t: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-voice-detect vulkan: vulkan-voice-detect uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-voice-detect mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f32-voice-detect - name: intel-sycl-f32-voice-detect-development alias: voice-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | voice-detect speaker recognition and voice analysis. voice-detect.cpp is a C++/ggml engine that produces L2-normalised speaker embeddings (ECAPA-TDNN, WeSpeaker ResNet34, 3D-Speaker ERes2Net, CAM++) for voice verification and 1:N identification, plus a wav2vec2 age / gender / emotion analysis head. It replaces the Python speaker-recognition backend and is exposed through the Voice* gRPC rpcs and the /v1/voice/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/voice-detect.cpp tags: - voice-recognition - speaker-verification - speaker-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-voice-detect default: cpu-voice-detect intel: intel-sycl-f16-voice-detect metal: metal-voice-detect nvidia: cuda12-voice-detect nvidia-cuda-12: cuda12-voice-detect nvidia-cuda-13: cuda13-voice-detect nvidia-l4t: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-voice-detect vulkan: vulkan-voice-detect uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-voice-detect mirrors: - localai/localai-backends:master-gpu-intel-sycl-f32-voice-detect - name: intel-sycl-f16-voice-detect alias: voice-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | voice-detect speaker recognition and voice analysis. voice-detect.cpp is a C++/ggml engine that produces L2-normalised speaker embeddings (ECAPA-TDNN, WeSpeaker ResNet34, 3D-Speaker ERes2Net, CAM++) for voice verification and 1:N identification, plus a wav2vec2 age / gender / emotion analysis head. It replaces the Python speaker-recognition backend and is exposed through the Voice* gRPC rpcs and the /v1/voice/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/voice-detect.cpp tags: - voice-recognition - speaker-verification - speaker-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-voice-detect default: cpu-voice-detect intel: intel-sycl-f16-voice-detect metal: metal-voice-detect nvidia: cuda12-voice-detect nvidia-cuda-12: cuda12-voice-detect nvidia-cuda-13: cuda13-voice-detect nvidia-l4t: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-voice-detect vulkan: vulkan-voice-detect uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-voice-detect mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f16-voice-detect - name: intel-sycl-f16-voice-detect-development alias: voice-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | voice-detect speaker recognition and voice analysis. voice-detect.cpp is a C++/ggml engine that produces L2-normalised speaker embeddings (ECAPA-TDNN, WeSpeaker ResNet34, 3D-Speaker ERes2Net, CAM++) for voice verification and 1:N identification, plus a wav2vec2 age / gender / emotion analysis head. It replaces the Python speaker-recognition backend and is exposed through the Voice* gRPC rpcs and the /v1/voice/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/voice-detect.cpp tags: - voice-recognition - speaker-verification - speaker-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-voice-detect default: cpu-voice-detect intel: intel-sycl-f16-voice-detect metal: metal-voice-detect nvidia: cuda12-voice-detect nvidia-cuda-12: cuda12-voice-detect nvidia-cuda-13: cuda13-voice-detect nvidia-l4t: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-voice-detect vulkan: vulkan-voice-detect uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-voice-detect mirrors: - localai/localai-backends:master-gpu-intel-sycl-f16-voice-detect - name: vulkan-voice-detect alias: voice-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | voice-detect speaker recognition and voice analysis. voice-detect.cpp is a C++/ggml engine that produces L2-normalised speaker embeddings (ECAPA-TDNN, WeSpeaker ResNet34, 3D-Speaker ERes2Net, CAM++) for voice verification and 1:N identification, plus a wav2vec2 age / gender / emotion analysis head. It replaces the Python speaker-recognition backend and is exposed through the Voice* gRPC rpcs and the /v1/voice/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/voice-detect.cpp tags: - voice-recognition - speaker-verification - speaker-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-voice-detect default: cpu-voice-detect intel: intel-sycl-f16-voice-detect metal: metal-voice-detect nvidia: cuda12-voice-detect nvidia-cuda-12: cuda12-voice-detect nvidia-cuda-13: cuda13-voice-detect nvidia-l4t: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-voice-detect vulkan: vulkan-voice-detect uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-voice-detect mirrors: - localai/localai-backends:latest-gpu-vulkan-voice-detect - name: vulkan-voice-detect-development alias: voice-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | voice-detect speaker recognition and voice analysis. voice-detect.cpp is a C++/ggml engine that produces L2-normalised speaker embeddings (ECAPA-TDNN, WeSpeaker ResNet34, 3D-Speaker ERes2Net, CAM++) for voice verification and 1:N identification, plus a wav2vec2 age / gender / emotion analysis head. It replaces the Python speaker-recognition backend and is exposed through the Voice* gRPC rpcs and the /v1/voice/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/voice-detect.cpp tags: - voice-recognition - speaker-verification - speaker-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-voice-detect default: cpu-voice-detect intel: intel-sycl-f16-voice-detect metal: metal-voice-detect nvidia: cuda12-voice-detect nvidia-cuda-12: cuda12-voice-detect nvidia-cuda-13: cuda13-voice-detect nvidia-l4t: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-voice-detect vulkan: vulkan-voice-detect uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-voice-detect mirrors: - localai/localai-backends:master-gpu-vulkan-voice-detect - name: cuda13-voice-detect alias: voice-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | voice-detect speaker recognition and voice analysis. voice-detect.cpp is a C++/ggml engine that produces L2-normalised speaker embeddings (ECAPA-TDNN, WeSpeaker ResNet34, 3D-Speaker ERes2Net, CAM++) for voice verification and 1:N identification, plus a wav2vec2 age / gender / emotion analysis head. It replaces the Python speaker-recognition backend and is exposed through the Voice* gRPC rpcs and the /v1/voice/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/voice-detect.cpp tags: - voice-recognition - speaker-verification - speaker-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-voice-detect default: cpu-voice-detect intel: intel-sycl-f16-voice-detect metal: metal-voice-detect nvidia: cuda12-voice-detect nvidia-cuda-12: cuda12-voice-detect nvidia-cuda-13: cuda13-voice-detect nvidia-l4t: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-voice-detect vulkan: vulkan-voice-detect uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-voice-detect mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-voice-detect - name: cuda13-voice-detect-development alias: voice-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | voice-detect speaker recognition and voice analysis. voice-detect.cpp is a C++/ggml engine that produces L2-normalised speaker embeddings (ECAPA-TDNN, WeSpeaker ResNet34, 3D-Speaker ERes2Net, CAM++) for voice verification and 1:N identification, plus a wav2vec2 age / gender / emotion analysis head. It replaces the Python speaker-recognition backend and is exposed through the Voice* gRPC rpcs and the /v1/voice/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/localai-org/voice-detect.cpp tags: - voice-recognition - speaker-verification - speaker-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-voice-detect default: cpu-voice-detect intel: intel-sycl-f16-voice-detect metal: metal-voice-detect nvidia: cuda12-voice-detect nvidia-cuda-12: cuda12-voice-detect nvidia-cuda-13: cuda13-voice-detect nvidia-l4t: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-voice-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-voice-detect vulkan: vulkan-voice-detect uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-voice-detect mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-voice-detect - name: face-detect-development alias: face-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | face-detect face detection, embedding, verification and analysis. face-detect.cpp is a C++/ggml engine that runs SCRFD / YuNet face detection and ArcFace / SFace 512-d (or 128-d) L2-normalised face embeddings for verification and 1:N identification, plus a landmark / age / gender analysis head. It replaces the Python insightface backend and is exposed through the Embedding, Detect and Face* gRPC rpcs and the /v1/face/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/face-detect.cpp tags: - face-recognition - face-verification - face-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-face-detect-development default: cpu-face-detect-development intel: intel-sycl-f16-face-detect-development metal: metal-face-detect-development nvidia: cuda12-face-detect-development nvidia-cuda-12: cuda12-face-detect-development nvidia-cuda-13: cuda13-face-detect-development nvidia-l4t: nvidia-l4t-arm64-face-detect-development nvidia-l4t-cuda-12: nvidia-l4t-arm64-face-detect-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-face-detect-development vulkan: vulkan-face-detect-development - name: nvidia-l4t-arm64-face-detect alias: face-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | face-detect face detection, embedding, verification and analysis. face-detect.cpp is a C++/ggml engine that runs SCRFD / YuNet face detection and ArcFace / SFace 512-d (or 128-d) L2-normalised face embeddings for verification and 1:N identification, plus a landmark / age / gender analysis head. It replaces the Python insightface backend and is exposed through the Embedding, Detect and Face* gRPC rpcs and the /v1/face/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/face-detect.cpp tags: - face-recognition - face-verification - face-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-face-detect default: cpu-face-detect intel: intel-sycl-f16-face-detect metal: metal-face-detect nvidia: cuda12-face-detect nvidia-cuda-12: cuda12-face-detect nvidia-cuda-13: cuda13-face-detect nvidia-l4t: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-face-detect vulkan: vulkan-face-detect uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-face-detect mirrors: - localai/localai-backends:latest-nvidia-l4t-arm64-face-detect - name: nvidia-l4t-arm64-face-detect-development alias: face-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | face-detect face detection, embedding, verification and analysis. face-detect.cpp is a C++/ggml engine that runs SCRFD / YuNet face detection and ArcFace / SFace 512-d (or 128-d) L2-normalised face embeddings for verification and 1:N identification, plus a landmark / age / gender analysis head. It replaces the Python insightface backend and is exposed through the Embedding, Detect and Face* gRPC rpcs and the /v1/face/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/face-detect.cpp tags: - face-recognition - face-verification - face-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-face-detect default: cpu-face-detect intel: intel-sycl-f16-face-detect metal: metal-face-detect nvidia: cuda12-face-detect nvidia-cuda-12: cuda12-face-detect nvidia-cuda-13: cuda13-face-detect nvidia-l4t: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-face-detect vulkan: vulkan-face-detect uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-face-detect mirrors: - localai/localai-backends:master-nvidia-l4t-arm64-face-detect - name: cuda13-nvidia-l4t-arm64-face-detect alias: face-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | face-detect face detection, embedding, verification and analysis. face-detect.cpp is a C++/ggml engine that runs SCRFD / YuNet face detection and ArcFace / SFace 512-d (or 128-d) L2-normalised face embeddings for verification and 1:N identification, plus a landmark / age / gender analysis head. It replaces the Python insightface backend and is exposed through the Embedding, Detect and Face* gRPC rpcs and the /v1/face/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/face-detect.cpp tags: - face-recognition - face-verification - face-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-face-detect default: cpu-face-detect intel: intel-sycl-f16-face-detect metal: metal-face-detect nvidia: cuda12-face-detect nvidia-cuda-12: cuda12-face-detect nvidia-cuda-13: cuda13-face-detect nvidia-l4t: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-face-detect vulkan: vulkan-face-detect uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-face-detect mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-face-detect - name: cuda13-nvidia-l4t-arm64-face-detect-development alias: face-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | face-detect face detection, embedding, verification and analysis. face-detect.cpp is a C++/ggml engine that runs SCRFD / YuNet face detection and ArcFace / SFace 512-d (or 128-d) L2-normalised face embeddings for verification and 1:N identification, plus a landmark / age / gender analysis head. It replaces the Python insightface backend and is exposed through the Embedding, Detect and Face* gRPC rpcs and the /v1/face/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/face-detect.cpp tags: - face-recognition - face-verification - face-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-face-detect default: cpu-face-detect intel: intel-sycl-f16-face-detect metal: metal-face-detect nvidia: cuda12-face-detect nvidia-cuda-12: cuda12-face-detect nvidia-cuda-13: cuda13-face-detect nvidia-l4t: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-face-detect vulkan: vulkan-face-detect uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-face-detect mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-face-detect - name: cpu-face-detect alias: face-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | face-detect face detection, embedding, verification and analysis. face-detect.cpp is a C++/ggml engine that runs SCRFD / YuNet face detection and ArcFace / SFace 512-d (or 128-d) L2-normalised face embeddings for verification and 1:N identification, plus a landmark / age / gender analysis head. It replaces the Python insightface backend and is exposed through the Embedding, Detect and Face* gRPC rpcs and the /v1/face/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/face-detect.cpp tags: - face-recognition - face-verification - face-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-face-detect default: cpu-face-detect intel: intel-sycl-f16-face-detect metal: metal-face-detect nvidia: cuda12-face-detect nvidia-cuda-12: cuda12-face-detect nvidia-cuda-13: cuda13-face-detect nvidia-l4t: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-face-detect vulkan: vulkan-face-detect uri: quay.io/go-skynet/local-ai-backends:latest-cpu-face-detect mirrors: - localai/localai-backends:latest-cpu-face-detect - name: cpu-face-detect-development alias: face-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | face-detect face detection, embedding, verification and analysis. face-detect.cpp is a C++/ggml engine that runs SCRFD / YuNet face detection and ArcFace / SFace 512-d (or 128-d) L2-normalised face embeddings for verification and 1:N identification, plus a landmark / age / gender analysis head. It replaces the Python insightface backend and is exposed through the Embedding, Detect and Face* gRPC rpcs and the /v1/face/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/face-detect.cpp tags: - face-recognition - face-verification - face-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-face-detect default: cpu-face-detect intel: intel-sycl-f16-face-detect metal: metal-face-detect nvidia: cuda12-face-detect nvidia-cuda-12: cuda12-face-detect nvidia-cuda-13: cuda13-face-detect nvidia-l4t: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-face-detect vulkan: vulkan-face-detect uri: quay.io/go-skynet/local-ai-backends:master-cpu-face-detect mirrors: - localai/localai-backends:master-cpu-face-detect - name: metal-face-detect alias: face-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | face-detect face detection, embedding, verification and analysis. face-detect.cpp is a C++/ggml engine that runs SCRFD / YuNet face detection and ArcFace / SFace 512-d (or 128-d) L2-normalised face embeddings for verification and 1:N identification, plus a landmark / age / gender analysis head. It replaces the Python insightface backend and is exposed through the Embedding, Detect and Face* gRPC rpcs and the /v1/face/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/face-detect.cpp tags: - face-recognition - face-verification - face-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-face-detect default: cpu-face-detect intel: intel-sycl-f16-face-detect metal: metal-face-detect nvidia: cuda12-face-detect nvidia-cuda-12: cuda12-face-detect nvidia-cuda-13: cuda13-face-detect nvidia-l4t: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-face-detect vulkan: vulkan-face-detect uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-face-detect mirrors: - localai/localai-backends:latest-metal-darwin-arm64-face-detect - name: metal-face-detect-development alias: face-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | face-detect face detection, embedding, verification and analysis. face-detect.cpp is a C++/ggml engine that runs SCRFD / YuNet face detection and ArcFace / SFace 512-d (or 128-d) L2-normalised face embeddings for verification and 1:N identification, plus a landmark / age / gender analysis head. It replaces the Python insightface backend and is exposed through the Embedding, Detect and Face* gRPC rpcs and the /v1/face/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/face-detect.cpp tags: - face-recognition - face-verification - face-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-face-detect default: cpu-face-detect intel: intel-sycl-f16-face-detect metal: metal-face-detect nvidia: cuda12-face-detect nvidia-cuda-12: cuda12-face-detect nvidia-cuda-13: cuda13-face-detect nvidia-l4t: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-face-detect vulkan: vulkan-face-detect uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-face-detect mirrors: - localai/localai-backends:master-metal-darwin-arm64-face-detect - name: cuda12-face-detect alias: face-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | face-detect face detection, embedding, verification and analysis. face-detect.cpp is a C++/ggml engine that runs SCRFD / YuNet face detection and ArcFace / SFace 512-d (or 128-d) L2-normalised face embeddings for verification and 1:N identification, plus a landmark / age / gender analysis head. It replaces the Python insightface backend and is exposed through the Embedding, Detect and Face* gRPC rpcs and the /v1/face/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/face-detect.cpp tags: - face-recognition - face-verification - face-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-face-detect default: cpu-face-detect intel: intel-sycl-f16-face-detect metal: metal-face-detect nvidia: cuda12-face-detect nvidia-cuda-12: cuda12-face-detect nvidia-cuda-13: cuda13-face-detect nvidia-l4t: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-face-detect vulkan: vulkan-face-detect uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-face-detect mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-face-detect - name: cuda12-face-detect-development alias: face-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | face-detect face detection, embedding, verification and analysis. face-detect.cpp is a C++/ggml engine that runs SCRFD / YuNet face detection and ArcFace / SFace 512-d (or 128-d) L2-normalised face embeddings for verification and 1:N identification, plus a landmark / age / gender analysis head. It replaces the Python insightface backend and is exposed through the Embedding, Detect and Face* gRPC rpcs and the /v1/face/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/face-detect.cpp tags: - face-recognition - face-verification - face-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-face-detect default: cpu-face-detect intel: intel-sycl-f16-face-detect metal: metal-face-detect nvidia: cuda12-face-detect nvidia-cuda-12: cuda12-face-detect nvidia-cuda-13: cuda13-face-detect nvidia-l4t: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-face-detect vulkan: vulkan-face-detect uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-face-detect mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-face-detect - name: rocm-face-detect alias: face-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | face-detect face detection, embedding, verification and analysis. face-detect.cpp is a C++/ggml engine that runs SCRFD / YuNet face detection and ArcFace / SFace 512-d (or 128-d) L2-normalised face embeddings for verification and 1:N identification, plus a landmark / age / gender analysis head. It replaces the Python insightface backend and is exposed through the Embedding, Detect and Face* gRPC rpcs and the /v1/face/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/face-detect.cpp tags: - face-recognition - face-verification - face-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-face-detect default: cpu-face-detect intel: intel-sycl-f16-face-detect metal: metal-face-detect nvidia: cuda12-face-detect nvidia-cuda-12: cuda12-face-detect nvidia-cuda-13: cuda13-face-detect nvidia-l4t: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-face-detect vulkan: vulkan-face-detect uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-face-detect mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-face-detect - name: rocm-face-detect-development alias: face-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | face-detect face detection, embedding, verification and analysis. face-detect.cpp is a C++/ggml engine that runs SCRFD / YuNet face detection and ArcFace / SFace 512-d (or 128-d) L2-normalised face embeddings for verification and 1:N identification, plus a landmark / age / gender analysis head. It replaces the Python insightface backend and is exposed through the Embedding, Detect and Face* gRPC rpcs and the /v1/face/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/face-detect.cpp tags: - face-recognition - face-verification - face-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-face-detect default: cpu-face-detect intel: intel-sycl-f16-face-detect metal: metal-face-detect nvidia: cuda12-face-detect nvidia-cuda-12: cuda12-face-detect nvidia-cuda-13: cuda13-face-detect nvidia-l4t: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-face-detect vulkan: vulkan-face-detect uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-face-detect mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-face-detect - name: intel-sycl-f32-face-detect alias: face-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | face-detect face detection, embedding, verification and analysis. face-detect.cpp is a C++/ggml engine that runs SCRFD / YuNet face detection and ArcFace / SFace 512-d (or 128-d) L2-normalised face embeddings for verification and 1:N identification, plus a landmark / age / gender analysis head. It replaces the Python insightface backend and is exposed through the Embedding, Detect and Face* gRPC rpcs and the /v1/face/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/face-detect.cpp tags: - face-recognition - face-verification - face-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-face-detect default: cpu-face-detect intel: intel-sycl-f16-face-detect metal: metal-face-detect nvidia: cuda12-face-detect nvidia-cuda-12: cuda12-face-detect nvidia-cuda-13: cuda13-face-detect nvidia-l4t: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-face-detect vulkan: vulkan-face-detect uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-face-detect mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f32-face-detect - name: intel-sycl-f32-face-detect-development alias: face-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | face-detect face detection, embedding, verification and analysis. face-detect.cpp is a C++/ggml engine that runs SCRFD / YuNet face detection and ArcFace / SFace 512-d (or 128-d) L2-normalised face embeddings for verification and 1:N identification, plus a landmark / age / gender analysis head. It replaces the Python insightface backend and is exposed through the Embedding, Detect and Face* gRPC rpcs and the /v1/face/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/face-detect.cpp tags: - face-recognition - face-verification - face-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-face-detect default: cpu-face-detect intel: intel-sycl-f16-face-detect metal: metal-face-detect nvidia: cuda12-face-detect nvidia-cuda-12: cuda12-face-detect nvidia-cuda-13: cuda13-face-detect nvidia-l4t: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-face-detect vulkan: vulkan-face-detect uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-face-detect mirrors: - localai/localai-backends:master-gpu-intel-sycl-f32-face-detect - name: intel-sycl-f16-face-detect alias: face-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | face-detect face detection, embedding, verification and analysis. face-detect.cpp is a C++/ggml engine that runs SCRFD / YuNet face detection and ArcFace / SFace 512-d (or 128-d) L2-normalised face embeddings for verification and 1:N identification, plus a landmark / age / gender analysis head. It replaces the Python insightface backend and is exposed through the Embedding, Detect and Face* gRPC rpcs and the /v1/face/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/face-detect.cpp tags: - face-recognition - face-verification - face-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-face-detect default: cpu-face-detect intel: intel-sycl-f16-face-detect metal: metal-face-detect nvidia: cuda12-face-detect nvidia-cuda-12: cuda12-face-detect nvidia-cuda-13: cuda13-face-detect nvidia-l4t: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-face-detect vulkan: vulkan-face-detect uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-face-detect mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f16-face-detect - name: intel-sycl-f16-face-detect-development alias: face-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | face-detect face detection, embedding, verification and analysis. face-detect.cpp is a C++/ggml engine that runs SCRFD / YuNet face detection and ArcFace / SFace 512-d (or 128-d) L2-normalised face embeddings for verification and 1:N identification, plus a landmark / age / gender analysis head. It replaces the Python insightface backend and is exposed through the Embedding, Detect and Face* gRPC rpcs and the /v1/face/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/face-detect.cpp tags: - face-recognition - face-verification - face-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-face-detect default: cpu-face-detect intel: intel-sycl-f16-face-detect metal: metal-face-detect nvidia: cuda12-face-detect nvidia-cuda-12: cuda12-face-detect nvidia-cuda-13: cuda13-face-detect nvidia-l4t: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-face-detect vulkan: vulkan-face-detect uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-face-detect mirrors: - localai/localai-backends:master-gpu-intel-sycl-f16-face-detect - name: vulkan-face-detect alias: face-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | face-detect face detection, embedding, verification and analysis. face-detect.cpp is a C++/ggml engine that runs SCRFD / YuNet face detection and ArcFace / SFace 512-d (or 128-d) L2-normalised face embeddings for verification and 1:N identification, plus a landmark / age / gender analysis head. It replaces the Python insightface backend and is exposed through the Embedding, Detect and Face* gRPC rpcs and the /v1/face/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/face-detect.cpp tags: - face-recognition - face-verification - face-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-face-detect default: cpu-face-detect intel: intel-sycl-f16-face-detect metal: metal-face-detect nvidia: cuda12-face-detect nvidia-cuda-12: cuda12-face-detect nvidia-cuda-13: cuda13-face-detect nvidia-l4t: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-face-detect vulkan: vulkan-face-detect uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-face-detect mirrors: - localai/localai-backends:latest-gpu-vulkan-face-detect - name: vulkan-face-detect-development alias: face-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | face-detect face detection, embedding, verification and analysis. face-detect.cpp is a C++/ggml engine that runs SCRFD / YuNet face detection and ArcFace / SFace 512-d (or 128-d) L2-normalised face embeddings for verification and 1:N identification, plus a landmark / age / gender analysis head. It replaces the Python insightface backend and is exposed through the Embedding, Detect and Face* gRPC rpcs and the /v1/face/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/face-detect.cpp tags: - face-recognition - face-verification - face-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-face-detect default: cpu-face-detect intel: intel-sycl-f16-face-detect metal: metal-face-detect nvidia: cuda12-face-detect nvidia-cuda-12: cuda12-face-detect nvidia-cuda-13: cuda13-face-detect nvidia-l4t: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-face-detect vulkan: vulkan-face-detect uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-face-detect mirrors: - localai/localai-backends:master-gpu-vulkan-face-detect - name: cuda13-face-detect alias: face-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | face-detect face detection, embedding, verification and analysis. face-detect.cpp is a C++/ggml engine that runs SCRFD / YuNet face detection and ArcFace / SFace 512-d (or 128-d) L2-normalised face embeddings for verification and 1:N identification, plus a landmark / age / gender analysis head. It replaces the Python insightface backend and is exposed through the Embedding, Detect and Face* gRPC rpcs and the /v1/face/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/face-detect.cpp tags: - face-recognition - face-verification - face-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-face-detect default: cpu-face-detect intel: intel-sycl-f16-face-detect metal: metal-face-detect nvidia: cuda12-face-detect nvidia-cuda-12: cuda12-face-detect nvidia-cuda-13: cuda13-face-detect nvidia-l4t: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-face-detect vulkan: vulkan-face-detect uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-face-detect mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-face-detect - name: cuda13-face-detect-development alias: face-detect license: mit icon: https://avatars.githubusercontent.com/u/95302084 description: | face-detect face detection, embedding, verification and analysis. face-detect.cpp is a C++/ggml engine that runs SCRFD / YuNet face detection and ArcFace / SFace 512-d (or 128-d) L2-normalised face embeddings for verification and 1:N identification, plus a landmark / age / gender analysis head. It replaces the Python insightface backend and is exposed through the Embedding, Detect and Face* gRPC rpcs and the /v1/face/* REST endpoints. It runs on CPU, NVIDIA CUDA, AMD ROCm/HIP, Intel SYCL, Vulkan and NVIDIA Jetson (L4T) targets. urls: - https://github.com/mudler/face-detect.cpp tags: - face-recognition - face-verification - face-embedding - CPU - GPU - CUDA - HIP capabilities: amd: rocm-face-detect default: cpu-face-detect intel: intel-sycl-f16-face-detect metal: metal-face-detect nvidia: cuda12-face-detect nvidia-cuda-12: cuda12-face-detect nvidia-cuda-13: cuda13-face-detect nvidia-l4t: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-12: nvidia-l4t-arm64-face-detect nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-face-detect vulkan: vulkan-face-detect uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-face-detect mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-face-detect - name: cpu-stablediffusion-ggml alias: stablediffusion-ggml license: mit icon: https://github.com/leejet/stable-diffusion.cpp/raw/master/assets/cat_with_sd_cpp_42.png description: | Stable Diffusion and Flux in pure C/C++ urls: - https://github.com/leejet/stable-diffusion.cpp tags: - image-generation - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-stablediffusion-ggml default: cpu-stablediffusion-ggml intel: intel-sycl-f16-stablediffusion-ggml metal: metal-stablediffusion-ggml nvidia: cuda12-stablediffusion-ggml nvidia-cuda-12: cuda12-stablediffusion-ggml nvidia-cuda-13: cuda13-stablediffusion-ggml nvidia-l4t: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-12: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-stablediffusion-ggml vulkan: vulkan-stablediffusion-ggml uri: quay.io/go-skynet/local-ai-backends:latest-cpu-stablediffusion-ggml mirrors: - localai/localai-backends:latest-cpu-stablediffusion-ggml - name: cpu-stablediffusion-ggml-development alias: stablediffusion-ggml license: mit icon: https://github.com/leejet/stable-diffusion.cpp/raw/master/assets/cat_with_sd_cpp_42.png description: | Stable Diffusion and Flux in pure C/C++ urls: - https://github.com/leejet/stable-diffusion.cpp tags: - image-generation - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-stablediffusion-ggml default: cpu-stablediffusion-ggml intel: intel-sycl-f16-stablediffusion-ggml metal: metal-stablediffusion-ggml nvidia: cuda12-stablediffusion-ggml nvidia-cuda-12: cuda12-stablediffusion-ggml nvidia-cuda-13: cuda13-stablediffusion-ggml nvidia-l4t: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-12: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-stablediffusion-ggml vulkan: vulkan-stablediffusion-ggml uri: quay.io/go-skynet/local-ai-backends:master-cpu-stablediffusion-ggml mirrors: - localai/localai-backends:master-cpu-stablediffusion-ggml - name: metal-stablediffusion-ggml alias: stablediffusion-ggml license: mit icon: https://github.com/leejet/stable-diffusion.cpp/raw/master/assets/cat_with_sd_cpp_42.png description: | Stable Diffusion and Flux in pure C/C++ urls: - https://github.com/leejet/stable-diffusion.cpp tags: - image-generation - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-stablediffusion-ggml default: cpu-stablediffusion-ggml intel: intel-sycl-f16-stablediffusion-ggml metal: metal-stablediffusion-ggml nvidia: cuda12-stablediffusion-ggml nvidia-cuda-12: cuda12-stablediffusion-ggml nvidia-cuda-13: cuda13-stablediffusion-ggml nvidia-l4t: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-12: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-stablediffusion-ggml vulkan: vulkan-stablediffusion-ggml uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-stablediffusion-ggml mirrors: - localai/localai-backends:latest-metal-darwin-arm64-stablediffusion-ggml - name: metal-stablediffusion-ggml-development alias: stablediffusion-ggml license: mit icon: https://github.com/leejet/stable-diffusion.cpp/raw/master/assets/cat_with_sd_cpp_42.png description: | Stable Diffusion and Flux in pure C/C++ urls: - https://github.com/leejet/stable-diffusion.cpp tags: - image-generation - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-stablediffusion-ggml default: cpu-stablediffusion-ggml intel: intel-sycl-f16-stablediffusion-ggml metal: metal-stablediffusion-ggml nvidia: cuda12-stablediffusion-ggml nvidia-cuda-12: cuda12-stablediffusion-ggml nvidia-cuda-13: cuda13-stablediffusion-ggml nvidia-l4t: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-12: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-stablediffusion-ggml vulkan: vulkan-stablediffusion-ggml uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-stablediffusion-ggml mirrors: - localai/localai-backends:master-metal-darwin-arm64-stablediffusion-ggml - name: vulkan-stablediffusion-ggml alias: stablediffusion-ggml license: mit icon: https://github.com/leejet/stable-diffusion.cpp/raw/master/assets/cat_with_sd_cpp_42.png description: | Stable Diffusion and Flux in pure C/C++ urls: - https://github.com/leejet/stable-diffusion.cpp tags: - image-generation - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-stablediffusion-ggml default: cpu-stablediffusion-ggml intel: intel-sycl-f16-stablediffusion-ggml metal: metal-stablediffusion-ggml nvidia: cuda12-stablediffusion-ggml nvidia-cuda-12: cuda12-stablediffusion-ggml nvidia-cuda-13: cuda13-stablediffusion-ggml nvidia-l4t: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-12: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-stablediffusion-ggml vulkan: vulkan-stablediffusion-ggml uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-stablediffusion-ggml mirrors: - localai/localai-backends:latest-gpu-vulkan-stablediffusion-ggml - name: vulkan-stablediffusion-ggml-development alias: stablediffusion-ggml license: mit icon: https://github.com/leejet/stable-diffusion.cpp/raw/master/assets/cat_with_sd_cpp_42.png description: | Stable Diffusion and Flux in pure C/C++ urls: - https://github.com/leejet/stable-diffusion.cpp tags: - image-generation - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-stablediffusion-ggml default: cpu-stablediffusion-ggml intel: intel-sycl-f16-stablediffusion-ggml metal: metal-stablediffusion-ggml nvidia: cuda12-stablediffusion-ggml nvidia-cuda-12: cuda12-stablediffusion-ggml nvidia-cuda-13: cuda13-stablediffusion-ggml nvidia-l4t: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-12: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-stablediffusion-ggml vulkan: vulkan-stablediffusion-ggml uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-stablediffusion-ggml mirrors: - localai/localai-backends:master-gpu-vulkan-stablediffusion-ggml - name: cuda12-stablediffusion-ggml alias: stablediffusion-ggml license: mit icon: https://github.com/leejet/stable-diffusion.cpp/raw/master/assets/cat_with_sd_cpp_42.png description: | Stable Diffusion and Flux in pure C/C++ urls: - https://github.com/leejet/stable-diffusion.cpp tags: - image-generation - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-stablediffusion-ggml default: cpu-stablediffusion-ggml intel: intel-sycl-f16-stablediffusion-ggml metal: metal-stablediffusion-ggml nvidia: cuda12-stablediffusion-ggml nvidia-cuda-12: cuda12-stablediffusion-ggml nvidia-cuda-13: cuda13-stablediffusion-ggml nvidia-l4t: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-12: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-stablediffusion-ggml vulkan: vulkan-stablediffusion-ggml uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-stablediffusion-ggml mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-stablediffusion-ggml - name: rocm-stablediffusion-ggml alias: stablediffusion-ggml license: mit icon: https://github.com/leejet/stable-diffusion.cpp/raw/master/assets/cat_with_sd_cpp_42.png description: | Stable Diffusion and Flux in pure C/C++ urls: - https://github.com/leejet/stable-diffusion.cpp tags: - image-generation - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-stablediffusion-ggml default: cpu-stablediffusion-ggml intel: intel-sycl-f16-stablediffusion-ggml metal: metal-stablediffusion-ggml nvidia: cuda12-stablediffusion-ggml nvidia-cuda-12: cuda12-stablediffusion-ggml nvidia-cuda-13: cuda13-stablediffusion-ggml nvidia-l4t: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-12: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-stablediffusion-ggml vulkan: vulkan-stablediffusion-ggml uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-stablediffusion-ggml mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-stablediffusion-ggml - name: intel-sycl-f32-stablediffusion-ggml alias: stablediffusion-ggml license: mit icon: https://github.com/leejet/stable-diffusion.cpp/raw/master/assets/cat_with_sd_cpp_42.png description: | Stable Diffusion and Flux in pure C/C++ urls: - https://github.com/leejet/stable-diffusion.cpp tags: - image-generation - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-stablediffusion-ggml default: cpu-stablediffusion-ggml intel: intel-sycl-f16-stablediffusion-ggml metal: metal-stablediffusion-ggml nvidia: cuda12-stablediffusion-ggml nvidia-cuda-12: cuda12-stablediffusion-ggml nvidia-cuda-13: cuda13-stablediffusion-ggml nvidia-l4t: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-12: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-stablediffusion-ggml vulkan: vulkan-stablediffusion-ggml uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-stablediffusion-ggml - name: intel-sycl-f16-stablediffusion-ggml alias: stablediffusion-ggml license: mit icon: https://github.com/leejet/stable-diffusion.cpp/raw/master/assets/cat_with_sd_cpp_42.png description: | Stable Diffusion and Flux in pure C/C++ urls: - https://github.com/leejet/stable-diffusion.cpp tags: - image-generation - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-stablediffusion-ggml default: cpu-stablediffusion-ggml intel: intel-sycl-f16-stablediffusion-ggml metal: metal-stablediffusion-ggml nvidia: cuda12-stablediffusion-ggml nvidia-cuda-12: cuda12-stablediffusion-ggml nvidia-cuda-13: cuda13-stablediffusion-ggml nvidia-l4t: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-12: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-stablediffusion-ggml vulkan: vulkan-stablediffusion-ggml uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-stablediffusion-ggml mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f16-stablediffusion-ggml - name: cuda12-stablediffusion-ggml-development alias: stablediffusion-ggml license: mit icon: https://github.com/leejet/stable-diffusion.cpp/raw/master/assets/cat_with_sd_cpp_42.png description: | Stable Diffusion and Flux in pure C/C++ urls: - https://github.com/leejet/stable-diffusion.cpp tags: - image-generation - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-stablediffusion-ggml default: cpu-stablediffusion-ggml intel: intel-sycl-f16-stablediffusion-ggml metal: metal-stablediffusion-ggml nvidia: cuda12-stablediffusion-ggml nvidia-cuda-12: cuda12-stablediffusion-ggml nvidia-cuda-13: cuda13-stablediffusion-ggml nvidia-l4t: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-12: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-stablediffusion-ggml vulkan: vulkan-stablediffusion-ggml uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-stablediffusion-ggml mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-stablediffusion-ggml - name: rocm-stablediffusion-ggml-development alias: stablediffusion-ggml license: mit icon: https://github.com/leejet/stable-diffusion.cpp/raw/master/assets/cat_with_sd_cpp_42.png description: | Stable Diffusion and Flux in pure C/C++ urls: - https://github.com/leejet/stable-diffusion.cpp tags: - image-generation - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-stablediffusion-ggml default: cpu-stablediffusion-ggml intel: intel-sycl-f16-stablediffusion-ggml metal: metal-stablediffusion-ggml nvidia: cuda12-stablediffusion-ggml nvidia-cuda-12: cuda12-stablediffusion-ggml nvidia-cuda-13: cuda13-stablediffusion-ggml nvidia-l4t: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-12: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-stablediffusion-ggml vulkan: vulkan-stablediffusion-ggml uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-stablediffusion-ggml mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-stablediffusion-ggml - name: intel-sycl-f32-stablediffusion-ggml-development alias: stablediffusion-ggml license: mit icon: https://github.com/leejet/stable-diffusion.cpp/raw/master/assets/cat_with_sd_cpp_42.png description: | Stable Diffusion and Flux in pure C/C++ urls: - https://github.com/leejet/stable-diffusion.cpp tags: - image-generation - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-stablediffusion-ggml default: cpu-stablediffusion-ggml intel: intel-sycl-f16-stablediffusion-ggml metal: metal-stablediffusion-ggml nvidia: cuda12-stablediffusion-ggml nvidia-cuda-12: cuda12-stablediffusion-ggml nvidia-cuda-13: cuda13-stablediffusion-ggml nvidia-l4t: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-12: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-stablediffusion-ggml vulkan: vulkan-stablediffusion-ggml uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-stablediffusion-ggml mirrors: - localai/localai-backends:master-gpu-intel-sycl-f32-stablediffusion-ggml - name: intel-sycl-f16-stablediffusion-ggml-development alias: stablediffusion-ggml license: mit icon: https://github.com/leejet/stable-diffusion.cpp/raw/master/assets/cat_with_sd_cpp_42.png description: | Stable Diffusion and Flux in pure C/C++ urls: - https://github.com/leejet/stable-diffusion.cpp tags: - image-generation - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-stablediffusion-ggml default: cpu-stablediffusion-ggml intel: intel-sycl-f16-stablediffusion-ggml metal: metal-stablediffusion-ggml nvidia: cuda12-stablediffusion-ggml nvidia-cuda-12: cuda12-stablediffusion-ggml nvidia-cuda-13: cuda13-stablediffusion-ggml nvidia-l4t: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-12: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-stablediffusion-ggml vulkan: vulkan-stablediffusion-ggml uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-stablediffusion-ggml mirrors: - localai/localai-backends:master-gpu-intel-sycl-f16-stablediffusion-ggml - name: nvidia-l4t-arm64-stablediffusion-ggml-development alias: stablediffusion-ggml license: mit icon: https://github.com/leejet/stable-diffusion.cpp/raw/master/assets/cat_with_sd_cpp_42.png description: | Stable Diffusion and Flux in pure C/C++ urls: - https://github.com/leejet/stable-diffusion.cpp tags: - image-generation - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-stablediffusion-ggml default: cpu-stablediffusion-ggml intel: intel-sycl-f16-stablediffusion-ggml metal: metal-stablediffusion-ggml nvidia: cuda12-stablediffusion-ggml nvidia-cuda-12: cuda12-stablediffusion-ggml nvidia-cuda-13: cuda13-stablediffusion-ggml nvidia-l4t: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-12: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-stablediffusion-ggml vulkan: vulkan-stablediffusion-ggml uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-stablediffusion-ggml mirrors: - localai/localai-backends:master-nvidia-l4t-arm64-stablediffusion-ggml - name: nvidia-l4t-arm64-stablediffusion-ggml alias: stablediffusion-ggml license: mit icon: https://github.com/leejet/stable-diffusion.cpp/raw/master/assets/cat_with_sd_cpp_42.png description: | Stable Diffusion and Flux in pure C/C++ urls: - https://github.com/leejet/stable-diffusion.cpp tags: - image-generation - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-stablediffusion-ggml default: cpu-stablediffusion-ggml intel: intel-sycl-f16-stablediffusion-ggml metal: metal-stablediffusion-ggml nvidia: cuda12-stablediffusion-ggml nvidia-cuda-12: cuda12-stablediffusion-ggml nvidia-cuda-13: cuda13-stablediffusion-ggml nvidia-l4t: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-12: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-stablediffusion-ggml vulkan: vulkan-stablediffusion-ggml uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-stablediffusion-ggml mirrors: - localai/localai-backends:latest-nvidia-l4t-arm64-stablediffusion-ggml - name: cuda13-nvidia-l4t-arm64-stablediffusion-ggml alias: stablediffusion-ggml license: mit icon: https://github.com/leejet/stable-diffusion.cpp/raw/master/assets/cat_with_sd_cpp_42.png description: | Stable Diffusion and Flux in pure C/C++ urls: - https://github.com/leejet/stable-diffusion.cpp tags: - image-generation - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-stablediffusion-ggml default: cpu-stablediffusion-ggml intel: intel-sycl-f16-stablediffusion-ggml metal: metal-stablediffusion-ggml nvidia: cuda12-stablediffusion-ggml nvidia-cuda-12: cuda12-stablediffusion-ggml nvidia-cuda-13: cuda13-stablediffusion-ggml nvidia-l4t: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-12: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-stablediffusion-ggml vulkan: vulkan-stablediffusion-ggml uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-stablediffusion-ggml mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-stablediffusion-ggml - name: cuda13-nvidia-l4t-arm64-stablediffusion-ggml-development alias: stablediffusion-ggml license: mit icon: https://github.com/leejet/stable-diffusion.cpp/raw/master/assets/cat_with_sd_cpp_42.png description: | Stable Diffusion and Flux in pure C/C++ urls: - https://github.com/leejet/stable-diffusion.cpp tags: - image-generation - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-stablediffusion-ggml default: cpu-stablediffusion-ggml intel: intel-sycl-f16-stablediffusion-ggml metal: metal-stablediffusion-ggml nvidia: cuda12-stablediffusion-ggml nvidia-cuda-12: cuda12-stablediffusion-ggml nvidia-cuda-13: cuda13-stablediffusion-ggml nvidia-l4t: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-12: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-stablediffusion-ggml vulkan: vulkan-stablediffusion-ggml uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-stablediffusion-ggml mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-stablediffusion-ggml - name: cuda13-stablediffusion-ggml alias: stablediffusion-ggml license: mit icon: https://github.com/leejet/stable-diffusion.cpp/raw/master/assets/cat_with_sd_cpp_42.png description: | Stable Diffusion and Flux in pure C/C++ urls: - https://github.com/leejet/stable-diffusion.cpp tags: - image-generation - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-stablediffusion-ggml default: cpu-stablediffusion-ggml intel: intel-sycl-f16-stablediffusion-ggml metal: metal-stablediffusion-ggml nvidia: cuda12-stablediffusion-ggml nvidia-cuda-12: cuda12-stablediffusion-ggml nvidia-cuda-13: cuda13-stablediffusion-ggml nvidia-l4t: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-12: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-stablediffusion-ggml vulkan: vulkan-stablediffusion-ggml uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-stablediffusion-ggml mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-stablediffusion-ggml - name: cuda13-stablediffusion-ggml-development alias: stablediffusion-ggml license: mit icon: https://github.com/leejet/stable-diffusion.cpp/raw/master/assets/cat_with_sd_cpp_42.png description: | Stable Diffusion and Flux in pure C/C++ urls: - https://github.com/leejet/stable-diffusion.cpp tags: - image-generation - CPU - GPU - Metal - CUDA - HIP capabilities: amd: rocm-stablediffusion-ggml default: cpu-stablediffusion-ggml intel: intel-sycl-f16-stablediffusion-ggml metal: metal-stablediffusion-ggml nvidia: cuda12-stablediffusion-ggml nvidia-cuda-12: cuda12-stablediffusion-ggml nvidia-cuda-13: cuda13-stablediffusion-ggml nvidia-l4t: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-12: nvidia-l4t-arm64-stablediffusion-ggml nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-stablediffusion-ggml vulkan: vulkan-stablediffusion-ggml uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-stablediffusion-ggml mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-stablediffusion-ggml - name: kimodocpp-development alias: kimodocpp license: apache-2.0 description: | kimodo.cpp text-to-motion: animated skeleton GLB on CPU and Vulkan. Apple Silicon uses the CPU runtime. urls: - https://github.com/localai-org/kimodo.cpp tags: - 3d-animation - text-to-motion - CPU - Vulkan capabilities: amd: vulkan-kimodocpp-development default: cpu-kimodocpp-development intel: vulkan-kimodocpp-development metal: cpu-darwin-arm64-kimodocpp-development nvidia: vulkan-kimodocpp-development nvidia-cuda-12: vulkan-kimodocpp-development nvidia-cuda-13: vulkan-kimodocpp-development vulkan: vulkan-kimodocpp-development - name: cpu-kimodocpp alias: kimodocpp license: apache-2.0 description: | kimodo.cpp text-to-motion: animated skeleton GLB on CPU and Vulkan. Apple Silicon uses the CPU runtime. urls: - https://github.com/localai-org/kimodo.cpp tags: - 3d-animation - text-to-motion - CPU - Vulkan capabilities: amd: vulkan-kimodocpp default: cpu-kimodocpp intel: vulkan-kimodocpp metal: cpu-darwin-arm64-kimodocpp nvidia: vulkan-kimodocpp nvidia-cuda-12: vulkan-kimodocpp nvidia-cuda-13: vulkan-kimodocpp vulkan: vulkan-kimodocpp uri: quay.io/go-skynet/local-ai-backends:latest-cpu-kimodocpp mirrors: - localai/localai-backends:latest-cpu-kimodocpp - name: cpu-kimodocpp-development alias: kimodocpp license: apache-2.0 description: | kimodo.cpp text-to-motion: animated skeleton GLB on CPU and Vulkan. Apple Silicon uses the CPU runtime. urls: - https://github.com/localai-org/kimodo.cpp tags: - 3d-animation - text-to-motion - CPU - Vulkan capabilities: amd: vulkan-kimodocpp default: cpu-kimodocpp intel: vulkan-kimodocpp metal: cpu-darwin-arm64-kimodocpp nvidia: vulkan-kimodocpp nvidia-cuda-12: vulkan-kimodocpp nvidia-cuda-13: vulkan-kimodocpp vulkan: vulkan-kimodocpp uri: quay.io/go-skynet/local-ai-backends:master-cpu-kimodocpp mirrors: - localai/localai-backends:master-cpu-kimodocpp - name: vulkan-kimodocpp alias: kimodocpp license: apache-2.0 description: | kimodo.cpp text-to-motion: animated skeleton GLB on CPU and Vulkan. Apple Silicon uses the CPU runtime. urls: - https://github.com/localai-org/kimodo.cpp tags: - 3d-animation - text-to-motion - CPU - Vulkan capabilities: amd: vulkan-kimodocpp default: cpu-kimodocpp intel: vulkan-kimodocpp metal: cpu-darwin-arm64-kimodocpp nvidia: vulkan-kimodocpp nvidia-cuda-12: vulkan-kimodocpp nvidia-cuda-13: vulkan-kimodocpp vulkan: vulkan-kimodocpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-kimodocpp mirrors: - localai/localai-backends:latest-gpu-vulkan-kimodocpp - name: vulkan-kimodocpp-development alias: kimodocpp license: apache-2.0 description: | kimodo.cpp text-to-motion: animated skeleton GLB on CPU and Vulkan. Apple Silicon uses the CPU runtime. urls: - https://github.com/localai-org/kimodo.cpp tags: - 3d-animation - text-to-motion - CPU - Vulkan capabilities: amd: vulkan-kimodocpp default: cpu-kimodocpp intel: vulkan-kimodocpp metal: cpu-darwin-arm64-kimodocpp nvidia: vulkan-kimodocpp nvidia-cuda-12: vulkan-kimodocpp nvidia-cuda-13: vulkan-kimodocpp vulkan: vulkan-kimodocpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-kimodocpp mirrors: - localai/localai-backends:master-gpu-vulkan-kimodocpp - name: cpu-darwin-arm64-kimodocpp alias: kimodocpp license: apache-2.0 description: | kimodo.cpp text-to-motion: animated skeleton GLB on CPU and Vulkan. Apple Silicon uses the CPU runtime. urls: - https://github.com/localai-org/kimodo.cpp tags: - 3d-animation - text-to-motion - CPU - Vulkan capabilities: amd: vulkan-kimodocpp default: cpu-kimodocpp intel: vulkan-kimodocpp metal: cpu-darwin-arm64-kimodocpp nvidia: vulkan-kimodocpp nvidia-cuda-12: vulkan-kimodocpp nvidia-cuda-13: vulkan-kimodocpp vulkan: vulkan-kimodocpp uri: quay.io/go-skynet/local-ai-backends:latest-cpu-darwin-arm64-kimodocpp mirrors: - localai/localai-backends:latest-cpu-darwin-arm64-kimodocpp - name: cpu-darwin-arm64-kimodocpp-development alias: kimodocpp license: apache-2.0 description: | kimodo.cpp text-to-motion: animated skeleton GLB on CPU and Vulkan. Apple Silicon uses the CPU runtime. urls: - https://github.com/localai-org/kimodo.cpp tags: - 3d-animation - text-to-motion - CPU - Vulkan capabilities: amd: vulkan-kimodocpp default: cpu-kimodocpp intel: vulkan-kimodocpp metal: cpu-darwin-arm64-kimodocpp nvidia: vulkan-kimodocpp nvidia-cuda-12: vulkan-kimodocpp nvidia-cuda-13: vulkan-kimodocpp vulkan: vulkan-kimodocpp uri: quay.io/go-skynet/local-ai-backends:master-cpu-darwin-arm64-kimodocpp mirrors: - localai/localai-backends:master-cpu-darwin-arm64-kimodocpp - name: gemxcpp-development alias: gemxcpp license: apache-2.0 description: | gem-x.cpp live human motion: SOMA and SMPL pose streams on CPU and Vulkan. Apple Silicon uses the CPU runtime. urls: - https://github.com/localai-org/gem-x.cpp tags: - motion - pose-estimation - CPU - Vulkan capabilities: amd: vulkan-gemxcpp-development default: cpu-gemxcpp-development intel: vulkan-gemxcpp-development metal: cpu-darwin-arm64-gemxcpp-development nvidia: vulkan-gemxcpp-development nvidia-cuda-12: vulkan-gemxcpp-development nvidia-cuda-13: vulkan-gemxcpp-development vulkan: vulkan-gemxcpp-development - name: cpu-gemxcpp alias: gemxcpp license: apache-2.0 description: | gem-x.cpp live human motion: SOMA and SMPL pose streams on CPU and Vulkan. Apple Silicon uses the CPU runtime. urls: - https://github.com/localai-org/gem-x.cpp tags: - motion - pose-estimation - CPU - Vulkan capabilities: amd: vulkan-gemxcpp default: cpu-gemxcpp intel: vulkan-gemxcpp metal: cpu-darwin-arm64-gemxcpp nvidia: vulkan-gemxcpp nvidia-cuda-12: vulkan-gemxcpp nvidia-cuda-13: vulkan-gemxcpp vulkan: vulkan-gemxcpp uri: quay.io/go-skynet/local-ai-backends:latest-cpu-gemxcpp mirrors: - localai/localai-backends:latest-cpu-gemxcpp - name: cpu-gemxcpp-development alias: gemxcpp license: apache-2.0 description: | gem-x.cpp live human motion: SOMA and SMPL pose streams on CPU and Vulkan. Apple Silicon uses the CPU runtime. urls: - https://github.com/localai-org/gem-x.cpp tags: - motion - pose-estimation - CPU - Vulkan capabilities: amd: vulkan-gemxcpp default: cpu-gemxcpp intel: vulkan-gemxcpp metal: cpu-darwin-arm64-gemxcpp nvidia: vulkan-gemxcpp nvidia-cuda-12: vulkan-gemxcpp nvidia-cuda-13: vulkan-gemxcpp vulkan: vulkan-gemxcpp uri: quay.io/go-skynet/local-ai-backends:master-cpu-gemxcpp mirrors: - localai/localai-backends:master-cpu-gemxcpp - name: vulkan-gemxcpp alias: gemxcpp license: apache-2.0 description: | gem-x.cpp live human motion: SOMA and SMPL pose streams on CPU and Vulkan. Apple Silicon uses the CPU runtime. urls: - https://github.com/localai-org/gem-x.cpp tags: - motion - pose-estimation - CPU - Vulkan capabilities: amd: vulkan-gemxcpp default: cpu-gemxcpp intel: vulkan-gemxcpp metal: cpu-darwin-arm64-gemxcpp nvidia: vulkan-gemxcpp nvidia-cuda-12: vulkan-gemxcpp nvidia-cuda-13: vulkan-gemxcpp vulkan: vulkan-gemxcpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-gemxcpp mirrors: - localai/localai-backends:latest-gpu-vulkan-gemxcpp - name: vulkan-gemxcpp-development alias: gemxcpp license: apache-2.0 description: | gem-x.cpp live human motion: SOMA and SMPL pose streams on CPU and Vulkan. Apple Silicon uses the CPU runtime. urls: - https://github.com/localai-org/gem-x.cpp tags: - motion - pose-estimation - CPU - Vulkan capabilities: amd: vulkan-gemxcpp default: cpu-gemxcpp intel: vulkan-gemxcpp metal: cpu-darwin-arm64-gemxcpp nvidia: vulkan-gemxcpp nvidia-cuda-12: vulkan-gemxcpp nvidia-cuda-13: vulkan-gemxcpp vulkan: vulkan-gemxcpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-gemxcpp mirrors: - localai/localai-backends:master-gpu-vulkan-gemxcpp - name: cpu-darwin-arm64-gemxcpp alias: gemxcpp license: apache-2.0 description: | gem-x.cpp live human motion: SOMA and SMPL pose streams on CPU and Vulkan. Apple Silicon uses the CPU runtime. urls: - https://github.com/localai-org/gem-x.cpp tags: - motion - pose-estimation - CPU - Vulkan capabilities: amd: vulkan-gemxcpp default: cpu-gemxcpp intel: vulkan-gemxcpp metal: cpu-darwin-arm64-gemxcpp nvidia: vulkan-gemxcpp nvidia-cuda-12: vulkan-gemxcpp nvidia-cuda-13: vulkan-gemxcpp vulkan: vulkan-gemxcpp uri: quay.io/go-skynet/local-ai-backends:latest-cpu-darwin-arm64-gemxcpp mirrors: - localai/localai-backends:latest-cpu-darwin-arm64-gemxcpp - name: cpu-darwin-arm64-gemxcpp-development alias: gemxcpp license: apache-2.0 description: | gem-x.cpp live human motion: SOMA and SMPL pose streams on CPU and Vulkan. Apple Silicon uses the CPU runtime. urls: - https://github.com/localai-org/gem-x.cpp tags: - motion - pose-estimation - CPU - Vulkan capabilities: amd: vulkan-gemxcpp default: cpu-gemxcpp intel: vulkan-gemxcpp metal: cpu-darwin-arm64-gemxcpp nvidia: vulkan-gemxcpp nvidia-cuda-12: vulkan-gemxcpp nvidia-cuda-13: vulkan-gemxcpp vulkan: vulkan-gemxcpp uri: quay.io/go-skynet/local-ai-backends:master-cpu-darwin-arm64-gemxcpp mirrors: - localai/localai-backends:master-cpu-darwin-arm64-gemxcpp - name: cpu-trellis2cpp alias: trellis2cpp license: mit description: | TRELLIS.2 image-to-3D generation (GLB meshes with PBR textures) in C++/ggml urls: - https://github.com/localai-org/trellis2cpp - https://github.com/microsoft/TRELLIS.2 tags: - image-to-3d - 3d-generation - CPU - GPU - CUDA - Metal capabilities: default: cpu-trellis2cpp metal: metal-trellis2cpp nvidia: cuda12-trellis2cpp nvidia-cuda-12: cuda12-trellis2cpp nvidia-cuda-13: cuda13-trellis2cpp nvidia-l4t: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-trellis2cpp vulkan: vulkan-trellis2cpp uri: quay.io/go-skynet/local-ai-backends:latest-cpu-trellis2cpp mirrors: - localai/localai-backends:latest-cpu-trellis2cpp - name: cpu-trellis2cpp-development alias: trellis2cpp license: mit description: | TRELLIS.2 image-to-3D generation (GLB meshes with PBR textures) in C++/ggml urls: - https://github.com/localai-org/trellis2cpp - https://github.com/microsoft/TRELLIS.2 tags: - image-to-3d - 3d-generation - CPU - GPU - CUDA - Metal capabilities: default: cpu-trellis2cpp metal: metal-trellis2cpp nvidia: cuda12-trellis2cpp nvidia-cuda-12: cuda12-trellis2cpp nvidia-cuda-13: cuda13-trellis2cpp nvidia-l4t: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-trellis2cpp vulkan: vulkan-trellis2cpp uri: quay.io/go-skynet/local-ai-backends:master-cpu-trellis2cpp mirrors: - localai/localai-backends:master-cpu-trellis2cpp - name: metal-trellis2cpp alias: trellis2cpp license: mit description: | TRELLIS.2 image-to-3D generation (GLB meshes with PBR textures) in C++/ggml urls: - https://github.com/localai-org/trellis2cpp - https://github.com/microsoft/TRELLIS.2 tags: - image-to-3d - 3d-generation - CPU - GPU - CUDA - Metal capabilities: default: cpu-trellis2cpp metal: metal-trellis2cpp nvidia: cuda12-trellis2cpp nvidia-cuda-12: cuda12-trellis2cpp nvidia-cuda-13: cuda13-trellis2cpp nvidia-l4t: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-trellis2cpp vulkan: vulkan-trellis2cpp uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-trellis2cpp mirrors: - localai/localai-backends:latest-metal-darwin-arm64-trellis2cpp - name: metal-trellis2cpp-development alias: trellis2cpp license: mit description: | TRELLIS.2 image-to-3D generation (GLB meshes with PBR textures) in C++/ggml urls: - https://github.com/localai-org/trellis2cpp - https://github.com/microsoft/TRELLIS.2 tags: - image-to-3d - 3d-generation - CPU - GPU - CUDA - Metal capabilities: default: cpu-trellis2cpp metal: metal-trellis2cpp nvidia: cuda12-trellis2cpp nvidia-cuda-12: cuda12-trellis2cpp nvidia-cuda-13: cuda13-trellis2cpp nvidia-l4t: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-trellis2cpp vulkan: vulkan-trellis2cpp uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-trellis2cpp mirrors: - localai/localai-backends:master-metal-darwin-arm64-trellis2cpp - name: vulkan-trellis2cpp alias: trellis2cpp license: mit description: | TRELLIS.2 image-to-3D generation (GLB meshes with PBR textures) in C++/ggml urls: - https://github.com/localai-org/trellis2cpp - https://github.com/microsoft/TRELLIS.2 tags: - image-to-3d - 3d-generation - CPU - GPU - CUDA - Metal capabilities: default: cpu-trellis2cpp metal: metal-trellis2cpp nvidia: cuda12-trellis2cpp nvidia-cuda-12: cuda12-trellis2cpp nvidia-cuda-13: cuda13-trellis2cpp nvidia-l4t: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-trellis2cpp vulkan: vulkan-trellis2cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-trellis2cpp mirrors: - localai/localai-backends:latest-gpu-vulkan-trellis2cpp - name: vulkan-trellis2cpp-development alias: trellis2cpp license: mit description: | TRELLIS.2 image-to-3D generation (GLB meshes with PBR textures) in C++/ggml urls: - https://github.com/localai-org/trellis2cpp - https://github.com/microsoft/TRELLIS.2 tags: - image-to-3d - 3d-generation - CPU - GPU - CUDA - Metal capabilities: default: cpu-trellis2cpp metal: metal-trellis2cpp nvidia: cuda12-trellis2cpp nvidia-cuda-12: cuda12-trellis2cpp nvidia-cuda-13: cuda13-trellis2cpp nvidia-l4t: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-trellis2cpp vulkan: vulkan-trellis2cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-trellis2cpp mirrors: - localai/localai-backends:master-gpu-vulkan-trellis2cpp - name: cuda12-trellis2cpp alias: trellis2cpp license: mit description: | TRELLIS.2 image-to-3D generation (GLB meshes with PBR textures) in C++/ggml urls: - https://github.com/localai-org/trellis2cpp - https://github.com/microsoft/TRELLIS.2 tags: - image-to-3d - 3d-generation - CPU - GPU - CUDA - Metal capabilities: default: cpu-trellis2cpp metal: metal-trellis2cpp nvidia: cuda12-trellis2cpp nvidia-cuda-12: cuda12-trellis2cpp nvidia-cuda-13: cuda13-trellis2cpp nvidia-l4t: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-trellis2cpp vulkan: vulkan-trellis2cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-trellis2cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-trellis2cpp - name: cuda12-trellis2cpp-development alias: trellis2cpp license: mit description: | TRELLIS.2 image-to-3D generation (GLB meshes with PBR textures) in C++/ggml urls: - https://github.com/localai-org/trellis2cpp - https://github.com/microsoft/TRELLIS.2 tags: - image-to-3d - 3d-generation - CPU - GPU - CUDA - Metal capabilities: default: cpu-trellis2cpp metal: metal-trellis2cpp nvidia: cuda12-trellis2cpp nvidia-cuda-12: cuda12-trellis2cpp nvidia-cuda-13: cuda13-trellis2cpp nvidia-l4t: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-trellis2cpp vulkan: vulkan-trellis2cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-trellis2cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-trellis2cpp - name: cuda13-trellis2cpp alias: trellis2cpp license: mit description: | TRELLIS.2 image-to-3D generation (GLB meshes with PBR textures) in C++/ggml urls: - https://github.com/localai-org/trellis2cpp - https://github.com/microsoft/TRELLIS.2 tags: - image-to-3d - 3d-generation - CPU - GPU - CUDA - Metal capabilities: default: cpu-trellis2cpp metal: metal-trellis2cpp nvidia: cuda12-trellis2cpp nvidia-cuda-12: cuda12-trellis2cpp nvidia-cuda-13: cuda13-trellis2cpp nvidia-l4t: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-trellis2cpp vulkan: vulkan-trellis2cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-trellis2cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-trellis2cpp - name: cuda13-trellis2cpp-development alias: trellis2cpp license: mit description: | TRELLIS.2 image-to-3D generation (GLB meshes with PBR textures) in C++/ggml urls: - https://github.com/localai-org/trellis2cpp - https://github.com/microsoft/TRELLIS.2 tags: - image-to-3d - 3d-generation - CPU - GPU - CUDA - Metal capabilities: default: cpu-trellis2cpp metal: metal-trellis2cpp nvidia: cuda12-trellis2cpp nvidia-cuda-12: cuda12-trellis2cpp nvidia-cuda-13: cuda13-trellis2cpp nvidia-l4t: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-trellis2cpp vulkan: vulkan-trellis2cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-trellis2cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-trellis2cpp - name: nvidia-l4t-arm64-trellis2cpp alias: trellis2cpp license: mit description: | TRELLIS.2 image-to-3D generation (GLB meshes with PBR textures) in C++/ggml urls: - https://github.com/localai-org/trellis2cpp - https://github.com/microsoft/TRELLIS.2 tags: - image-to-3d - 3d-generation - CPU - GPU - CUDA - Metal capabilities: default: cpu-trellis2cpp metal: metal-trellis2cpp nvidia: cuda12-trellis2cpp nvidia-cuda-12: cuda12-trellis2cpp nvidia-cuda-13: cuda13-trellis2cpp nvidia-l4t: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-trellis2cpp vulkan: vulkan-trellis2cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-trellis2cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-arm64-trellis2cpp - name: nvidia-l4t-arm64-trellis2cpp-development alias: trellis2cpp license: mit description: | TRELLIS.2 image-to-3D generation (GLB meshes with PBR textures) in C++/ggml urls: - https://github.com/localai-org/trellis2cpp - https://github.com/microsoft/TRELLIS.2 tags: - image-to-3d - 3d-generation - CPU - GPU - CUDA - Metal capabilities: default: cpu-trellis2cpp metal: metal-trellis2cpp nvidia: cuda12-trellis2cpp nvidia-cuda-12: cuda12-trellis2cpp nvidia-cuda-13: cuda13-trellis2cpp nvidia-l4t: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-trellis2cpp vulkan: vulkan-trellis2cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-trellis2cpp mirrors: - localai/localai-backends:master-nvidia-l4t-arm64-trellis2cpp - name: cuda13-nvidia-l4t-arm64-trellis2cpp alias: trellis2cpp license: mit description: | TRELLIS.2 image-to-3D generation (GLB meshes with PBR textures) in C++/ggml urls: - https://github.com/localai-org/trellis2cpp - https://github.com/microsoft/TRELLIS.2 tags: - image-to-3d - 3d-generation - CPU - GPU - CUDA - Metal capabilities: default: cpu-trellis2cpp metal: metal-trellis2cpp nvidia: cuda12-trellis2cpp nvidia-cuda-12: cuda12-trellis2cpp nvidia-cuda-13: cuda13-trellis2cpp nvidia-l4t: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-trellis2cpp vulkan: vulkan-trellis2cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-trellis2cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-trellis2cpp - name: cuda13-nvidia-l4t-arm64-trellis2cpp-development alias: trellis2cpp license: mit description: | TRELLIS.2 image-to-3D generation (GLB meshes with PBR textures) in C++/ggml urls: - https://github.com/localai-org/trellis2cpp - https://github.com/microsoft/TRELLIS.2 tags: - image-to-3d - 3d-generation - CPU - GPU - CUDA - Metal capabilities: default: cpu-trellis2cpp metal: metal-trellis2cpp nvidia: cuda12-trellis2cpp nvidia-cuda-12: cuda12-trellis2cpp nvidia-cuda-13: cuda13-trellis2cpp nvidia-l4t: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-trellis2cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-trellis2cpp vulkan: vulkan-trellis2cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-trellis2cpp mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-trellis2cpp - name: cpu-privacy-filter alias: privacy-filter license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/5fd5e18a90b6dc4633f6d292/QPiv8pt4JNxr0FdGnpFef.png description: | Standalone GGML engine (privacy-filter.cpp) for the OpenMed privacy-filter PII/NER token-classification model family. It runs the openai-privacy-filter architecture (a gpt-oss-style sparse-MoE bidirectional token classifier) on stock upstream GGML — no llama.cpp coupling and no Python — and serves the TokenClassify RPC (constrained BIOES Viterbi decode into UTF-8 byte-offset entity spans) used by LocalAI's NER PII redaction tier. urls: - https://github.com/localai-org/privacy-filter.cpp tags: - token-classification - ner - pii - privacy - CPU - GPU capabilities: amd: vulkan-privacy-filter default: cpu-privacy-filter intel: vulkan-privacy-filter metal: metal-privacy-filter nvidia: vulkan-privacy-filter nvidia-cuda-12: vulkan-privacy-filter nvidia-cuda-13: cuda13-privacy-filter vulkan: vulkan-privacy-filter uri: quay.io/go-skynet/local-ai-backends:latest-cpu-privacy-filter mirrors: - localai/localai-backends:latest-cpu-privacy-filter - name: cpu-privacy-filter-development alias: privacy-filter license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/5fd5e18a90b6dc4633f6d292/QPiv8pt4JNxr0FdGnpFef.png description: | Standalone GGML engine (privacy-filter.cpp) for the OpenMed privacy-filter PII/NER token-classification model family. It runs the openai-privacy-filter architecture (a gpt-oss-style sparse-MoE bidirectional token classifier) on stock upstream GGML — no llama.cpp coupling and no Python — and serves the TokenClassify RPC (constrained BIOES Viterbi decode into UTF-8 byte-offset entity spans) used by LocalAI's NER PII redaction tier. urls: - https://github.com/localai-org/privacy-filter.cpp tags: - token-classification - ner - pii - privacy - CPU - GPU capabilities: amd: vulkan-privacy-filter default: cpu-privacy-filter intel: vulkan-privacy-filter metal: metal-privacy-filter nvidia: vulkan-privacy-filter nvidia-cuda-12: vulkan-privacy-filter nvidia-cuda-13: cuda13-privacy-filter vulkan: vulkan-privacy-filter uri: quay.io/go-skynet/local-ai-backends:master-cpu-privacy-filter mirrors: - localai/localai-backends:master-cpu-privacy-filter - name: vulkan-privacy-filter alias: privacy-filter license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/5fd5e18a90b6dc4633f6d292/QPiv8pt4JNxr0FdGnpFef.png description: | Standalone GGML engine (privacy-filter.cpp) for the OpenMed privacy-filter PII/NER token-classification model family. It runs the openai-privacy-filter architecture (a gpt-oss-style sparse-MoE bidirectional token classifier) on stock upstream GGML — no llama.cpp coupling and no Python — and serves the TokenClassify RPC (constrained BIOES Viterbi decode into UTF-8 byte-offset entity spans) used by LocalAI's NER PII redaction tier. urls: - https://github.com/localai-org/privacy-filter.cpp tags: - token-classification - ner - pii - privacy - CPU - GPU capabilities: amd: vulkan-privacy-filter default: cpu-privacy-filter intel: vulkan-privacy-filter metal: metal-privacy-filter nvidia: vulkan-privacy-filter nvidia-cuda-12: vulkan-privacy-filter nvidia-cuda-13: cuda13-privacy-filter vulkan: vulkan-privacy-filter uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-privacy-filter mirrors: - localai/localai-backends:latest-gpu-vulkan-privacy-filter - name: vulkan-privacy-filter-development alias: privacy-filter license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/5fd5e18a90b6dc4633f6d292/QPiv8pt4JNxr0FdGnpFef.png description: | Standalone GGML engine (privacy-filter.cpp) for the OpenMed privacy-filter PII/NER token-classification model family. It runs the openai-privacy-filter architecture (a gpt-oss-style sparse-MoE bidirectional token classifier) on stock upstream GGML — no llama.cpp coupling and no Python — and serves the TokenClassify RPC (constrained BIOES Viterbi decode into UTF-8 byte-offset entity spans) used by LocalAI's NER PII redaction tier. urls: - https://github.com/localai-org/privacy-filter.cpp tags: - token-classification - ner - pii - privacy - CPU - GPU capabilities: amd: vulkan-privacy-filter default: cpu-privacy-filter intel: vulkan-privacy-filter metal: metal-privacy-filter nvidia: vulkan-privacy-filter nvidia-cuda-12: vulkan-privacy-filter nvidia-cuda-13: cuda13-privacy-filter vulkan: vulkan-privacy-filter uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-privacy-filter mirrors: - localai/localai-backends:master-gpu-vulkan-privacy-filter - name: metal-privacy-filter alias: privacy-filter license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/5fd5e18a90b6dc4633f6d292/QPiv8pt4JNxr0FdGnpFef.png description: | Standalone GGML engine (privacy-filter.cpp) for the OpenMed privacy-filter PII/NER token-classification model family. It runs the openai-privacy-filter architecture (a gpt-oss-style sparse-MoE bidirectional token classifier) on stock upstream GGML — no llama.cpp coupling and no Python — and serves the TokenClassify RPC (constrained BIOES Viterbi decode into UTF-8 byte-offset entity spans) used by LocalAI's NER PII redaction tier. urls: - https://github.com/localai-org/privacy-filter.cpp tags: - token-classification - ner - pii - privacy - CPU - GPU capabilities: amd: vulkan-privacy-filter default: cpu-privacy-filter intel: vulkan-privacy-filter metal: metal-privacy-filter nvidia: vulkan-privacy-filter nvidia-cuda-12: vulkan-privacy-filter nvidia-cuda-13: cuda13-privacy-filter vulkan: vulkan-privacy-filter uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-privacy-filter mirrors: - localai/localai-backends:latest-metal-darwin-arm64-privacy-filter - name: metal-privacy-filter-development alias: privacy-filter license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/5fd5e18a90b6dc4633f6d292/QPiv8pt4JNxr0FdGnpFef.png description: | Standalone GGML engine (privacy-filter.cpp) for the OpenMed privacy-filter PII/NER token-classification model family. It runs the openai-privacy-filter architecture (a gpt-oss-style sparse-MoE bidirectional token classifier) on stock upstream GGML — no llama.cpp coupling and no Python — and serves the TokenClassify RPC (constrained BIOES Viterbi decode into UTF-8 byte-offset entity spans) used by LocalAI's NER PII redaction tier. urls: - https://github.com/localai-org/privacy-filter.cpp tags: - token-classification - ner - pii - privacy - CPU - GPU capabilities: amd: vulkan-privacy-filter default: cpu-privacy-filter intel: vulkan-privacy-filter metal: metal-privacy-filter nvidia: vulkan-privacy-filter nvidia-cuda-12: vulkan-privacy-filter nvidia-cuda-13: cuda13-privacy-filter vulkan: vulkan-privacy-filter uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-privacy-filter mirrors: - localai/localai-backends:master-metal-darwin-arm64-privacy-filter - name: cuda13-privacy-filter alias: privacy-filter license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/5fd5e18a90b6dc4633f6d292/QPiv8pt4JNxr0FdGnpFef.png description: | Standalone GGML engine (privacy-filter.cpp) for the OpenMed privacy-filter PII/NER token-classification model family. It runs the openai-privacy-filter architecture (a gpt-oss-style sparse-MoE bidirectional token classifier) on stock upstream GGML — no llama.cpp coupling and no Python — and serves the TokenClassify RPC (constrained BIOES Viterbi decode into UTF-8 byte-offset entity spans) used by LocalAI's NER PII redaction tier. urls: - https://github.com/localai-org/privacy-filter.cpp tags: - token-classification - ner - pii - privacy - CPU - GPU capabilities: amd: vulkan-privacy-filter default: cpu-privacy-filter intel: vulkan-privacy-filter metal: metal-privacy-filter nvidia: vulkan-privacy-filter nvidia-cuda-12: vulkan-privacy-filter nvidia-cuda-13: cuda13-privacy-filter vulkan: vulkan-privacy-filter uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-privacy-filter mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-privacy-filter - name: cuda13-privacy-filter-development alias: privacy-filter license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/5fd5e18a90b6dc4633f6d292/QPiv8pt4JNxr0FdGnpFef.png description: | Standalone GGML engine (privacy-filter.cpp) for the OpenMed privacy-filter PII/NER token-classification model family. It runs the openai-privacy-filter architecture (a gpt-oss-style sparse-MoE bidirectional token classifier) on stock upstream GGML — no llama.cpp coupling and no Python — and serves the TokenClassify RPC (constrained BIOES Viterbi decode into UTF-8 byte-offset entity spans) used by LocalAI's NER PII redaction tier. urls: - https://github.com/localai-org/privacy-filter.cpp tags: - token-classification - ner - pii - privacy - CPU - GPU capabilities: amd: vulkan-privacy-filter default: cpu-privacy-filter intel: vulkan-privacy-filter metal: metal-privacy-filter nvidia: vulkan-privacy-filter nvidia-cuda-12: vulkan-privacy-filter nvidia-cuda-13: cuda13-privacy-filter vulkan: vulkan-privacy-filter uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-privacy-filter mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-privacy-filter - name: vllm-development alias: vllm license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM is a fast and easy-to-use library for LLM inference and serving. Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry. vLLM is fast with: State-of-the-art serving throughput Efficient management of attention key and value memory with PagedAttention Continuous batching of incoming requests Fast model execution with CUDA/HIP graph Quantizations: GPTQ, AWQ, AutoRound, INT4, INT8, and FP8 Optimized CUDA kernels, including integration with FlashAttention and FlashInfer Speculative decoding Chunked prefill urls: - https://github.com/vllm-project/vllm tags: - text-to-text - multimodal - GPTQ - AWQ - AutoRound - INT4 - INT8 - FP8 capabilities: amd: rocm-vllm-development cpu: cpu-vllm-development intel: intel-vllm-development metal: metal-vllm-development nvidia: cuda12-vllm-development nvidia-cuda-12: cuda12-vllm-development nvidia-cuda-13: cuda13-vllm-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm-development - name: metal-vllm alias: vllm license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM is a fast and easy-to-use library for LLM inference and serving. Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry. vLLM is fast with: State-of-the-art serving throughput Efficient management of attention key and value memory with PagedAttention Continuous batching of incoming requests Fast model execution with CUDA/HIP graph Quantizations: GPTQ, AWQ, AutoRound, INT4, INT8, and FP8 Optimized CUDA kernels, including integration with FlashAttention and FlashInfer Speculative decoding Chunked prefill urls: - https://github.com/vllm-project/vllm tags: - text-to-text - multimodal - GPTQ - AWQ - AutoRound - INT4 - INT8 - FP8 capabilities: amd: rocm-vllm cpu: cpu-vllm intel: intel-vllm metal: metal-vllm nvidia: cuda12-vllm nvidia-cuda-12: cuda12-vllm nvidia-cuda-13: cuda13-vllm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-vllm mirrors: - localai/localai-backends:latest-metal-darwin-arm64-vllm - name: metal-vllm-development alias: vllm license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM is a fast and easy-to-use library for LLM inference and serving. Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry. vLLM is fast with: State-of-the-art serving throughput Efficient management of attention key and value memory with PagedAttention Continuous batching of incoming requests Fast model execution with CUDA/HIP graph Quantizations: GPTQ, AWQ, AutoRound, INT4, INT8, and FP8 Optimized CUDA kernels, including integration with FlashAttention and FlashInfer Speculative decoding Chunked prefill urls: - https://github.com/vllm-project/vllm tags: - text-to-text - multimodal - GPTQ - AWQ - AutoRound - INT4 - INT8 - FP8 capabilities: amd: rocm-vllm cpu: cpu-vllm intel: intel-vllm metal: metal-vllm nvidia: cuda12-vllm nvidia-cuda-12: cuda12-vllm nvidia-cuda-13: cuda13-vllm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-vllm mirrors: - localai/localai-backends:master-metal-darwin-arm64-vllm - name: cuda12-vllm alias: vllm license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM is a fast and easy-to-use library for LLM inference and serving. Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry. vLLM is fast with: State-of-the-art serving throughput Efficient management of attention key and value memory with PagedAttention Continuous batching of incoming requests Fast model execution with CUDA/HIP graph Quantizations: GPTQ, AWQ, AutoRound, INT4, INT8, and FP8 Optimized CUDA kernels, including integration with FlashAttention and FlashInfer Speculative decoding Chunked prefill urls: - https://github.com/vllm-project/vllm tags: - text-to-text - multimodal - GPTQ - AWQ - AutoRound - INT4 - INT8 - FP8 capabilities: amd: rocm-vllm cpu: cpu-vllm intel: intel-vllm metal: metal-vllm nvidia: cuda12-vllm nvidia-cuda-12: cuda12-vllm nvidia-cuda-13: cuda13-vllm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-vllm mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-vllm - name: cuda13-vllm alias: vllm license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM is a fast and easy-to-use library for LLM inference and serving. Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry. vLLM is fast with: State-of-the-art serving throughput Efficient management of attention key and value memory with PagedAttention Continuous batching of incoming requests Fast model execution with CUDA/HIP graph Quantizations: GPTQ, AWQ, AutoRound, INT4, INT8, and FP8 Optimized CUDA kernels, including integration with FlashAttention and FlashInfer Speculative decoding Chunked prefill urls: - https://github.com/vllm-project/vllm tags: - text-to-text - multimodal - GPTQ - AWQ - AutoRound - INT4 - INT8 - FP8 capabilities: amd: rocm-vllm cpu: cpu-vllm intel: intel-vllm metal: metal-vllm nvidia: cuda12-vllm nvidia-cuda-12: cuda12-vllm nvidia-cuda-13: cuda13-vllm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-vllm mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-vllm - name: cuda13-nvidia-l4t-arm64-vllm alias: vllm license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM is a fast and easy-to-use library for LLM inference and serving. Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry. vLLM is fast with: State-of-the-art serving throughput Efficient management of attention key and value memory with PagedAttention Continuous batching of incoming requests Fast model execution with CUDA/HIP graph Quantizations: GPTQ, AWQ, AutoRound, INT4, INT8, and FP8 Optimized CUDA kernels, including integration with FlashAttention and FlashInfer Speculative decoding Chunked prefill urls: - https://github.com/vllm-project/vllm tags: - text-to-text - multimodal - GPTQ - AWQ - AutoRound - INT4 - INT8 - FP8 capabilities: amd: rocm-vllm cpu: cpu-vllm intel: intel-vllm metal: metal-vllm nvidia: cuda12-vllm nvidia-cuda-12: cuda12-vllm nvidia-cuda-13: cuda13-vllm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-vllm mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-vllm - name: rocm-vllm alias: vllm license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM is a fast and easy-to-use library for LLM inference and serving. Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry. vLLM is fast with: State-of-the-art serving throughput Efficient management of attention key and value memory with PagedAttention Continuous batching of incoming requests Fast model execution with CUDA/HIP graph Quantizations: GPTQ, AWQ, AutoRound, INT4, INT8, and FP8 Optimized CUDA kernels, including integration with FlashAttention and FlashInfer Speculative decoding Chunked prefill urls: - https://github.com/vllm-project/vllm tags: - text-to-text - multimodal - GPTQ - AWQ - AutoRound - INT4 - INT8 - FP8 capabilities: amd: rocm-vllm cpu: cpu-vllm intel: intel-vllm metal: metal-vllm nvidia: cuda12-vllm nvidia-cuda-12: cuda12-vllm nvidia-cuda-13: cuda13-vllm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-vllm mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-vllm - name: intel-vllm alias: vllm license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM is a fast and easy-to-use library for LLM inference and serving. Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry. vLLM is fast with: State-of-the-art serving throughput Efficient management of attention key and value memory with PagedAttention Continuous batching of incoming requests Fast model execution with CUDA/HIP graph Quantizations: GPTQ, AWQ, AutoRound, INT4, INT8, and FP8 Optimized CUDA kernels, including integration with FlashAttention and FlashInfer Speculative decoding Chunked prefill urls: - https://github.com/vllm-project/vllm tags: - text-to-text - multimodal - GPTQ - AWQ - AutoRound - INT4 - INT8 - FP8 capabilities: amd: rocm-vllm cpu: cpu-vllm intel: intel-vllm metal: metal-vllm nvidia: cuda12-vllm nvidia-cuda-12: cuda12-vllm nvidia-cuda-13: cuda13-vllm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-vllm mirrors: - localai/localai-backends:latest-gpu-intel-vllm - name: cpu-vllm alias: vllm license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM is a fast and easy-to-use library for LLM inference and serving. Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry. vLLM is fast with: State-of-the-art serving throughput Efficient management of attention key and value memory with PagedAttention Continuous batching of incoming requests Fast model execution with CUDA/HIP graph Quantizations: GPTQ, AWQ, AutoRound, INT4, INT8, and FP8 Optimized CUDA kernels, including integration with FlashAttention and FlashInfer Speculative decoding Chunked prefill urls: - https://github.com/vllm-project/vllm tags: - text-to-text - multimodal - GPTQ - AWQ - AutoRound - INT4 - INT8 - FP8 capabilities: amd: rocm-vllm cpu: cpu-vllm intel: intel-vllm metal: metal-vllm nvidia: cuda12-vllm nvidia-cuda-12: cuda12-vllm nvidia-cuda-13: cuda13-vllm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm uri: quay.io/go-skynet/local-ai-backends:latest-cpu-vllm mirrors: - localai/localai-backends:latest-cpu-vllm - name: cuda12-vllm-development alias: vllm license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM is a fast and easy-to-use library for LLM inference and serving. Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry. vLLM is fast with: State-of-the-art serving throughput Efficient management of attention key and value memory with PagedAttention Continuous batching of incoming requests Fast model execution with CUDA/HIP graph Quantizations: GPTQ, AWQ, AutoRound, INT4, INT8, and FP8 Optimized CUDA kernels, including integration with FlashAttention and FlashInfer Speculative decoding Chunked prefill urls: - https://github.com/vllm-project/vllm tags: - text-to-text - multimodal - GPTQ - AWQ - AutoRound - INT4 - INT8 - FP8 capabilities: amd: rocm-vllm cpu: cpu-vllm intel: intel-vllm metal: metal-vllm nvidia: cuda12-vllm nvidia-cuda-12: cuda12-vllm nvidia-cuda-13: cuda13-vllm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-vllm mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-vllm - name: cuda13-vllm-development alias: vllm license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM is a fast and easy-to-use library for LLM inference and serving. Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry. vLLM is fast with: State-of-the-art serving throughput Efficient management of attention key and value memory with PagedAttention Continuous batching of incoming requests Fast model execution with CUDA/HIP graph Quantizations: GPTQ, AWQ, AutoRound, INT4, INT8, and FP8 Optimized CUDA kernels, including integration with FlashAttention and FlashInfer Speculative decoding Chunked prefill urls: - https://github.com/vllm-project/vllm tags: - text-to-text - multimodal - GPTQ - AWQ - AutoRound - INT4 - INT8 - FP8 capabilities: amd: rocm-vllm cpu: cpu-vllm intel: intel-vllm metal: metal-vllm nvidia: cuda12-vllm nvidia-cuda-12: cuda12-vllm nvidia-cuda-13: cuda13-vllm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-vllm mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-vllm - name: cuda13-nvidia-l4t-arm64-vllm-development alias: vllm license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM is a fast and easy-to-use library for LLM inference and serving. Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry. vLLM is fast with: State-of-the-art serving throughput Efficient management of attention key and value memory with PagedAttention Continuous batching of incoming requests Fast model execution with CUDA/HIP graph Quantizations: GPTQ, AWQ, AutoRound, INT4, INT8, and FP8 Optimized CUDA kernels, including integration with FlashAttention and FlashInfer Speculative decoding Chunked prefill urls: - https://github.com/vllm-project/vllm tags: - text-to-text - multimodal - GPTQ - AWQ - AutoRound - INT4 - INT8 - FP8 capabilities: amd: rocm-vllm cpu: cpu-vllm intel: intel-vllm metal: metal-vllm nvidia: cuda12-vllm nvidia-cuda-12: cuda12-vllm nvidia-cuda-13: cuda13-vllm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-vllm mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-vllm - name: rocm-vllm-development alias: vllm license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM is a fast and easy-to-use library for LLM inference and serving. Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry. vLLM is fast with: State-of-the-art serving throughput Efficient management of attention key and value memory with PagedAttention Continuous batching of incoming requests Fast model execution with CUDA/HIP graph Quantizations: GPTQ, AWQ, AutoRound, INT4, INT8, and FP8 Optimized CUDA kernels, including integration with FlashAttention and FlashInfer Speculative decoding Chunked prefill urls: - https://github.com/vllm-project/vllm tags: - text-to-text - multimodal - GPTQ - AWQ - AutoRound - INT4 - INT8 - FP8 capabilities: amd: rocm-vllm cpu: cpu-vllm intel: intel-vllm metal: metal-vllm nvidia: cuda12-vllm nvidia-cuda-12: cuda12-vllm nvidia-cuda-13: cuda13-vllm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-vllm mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-vllm - name: intel-vllm-development alias: vllm license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM is a fast and easy-to-use library for LLM inference and serving. Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry. vLLM is fast with: State-of-the-art serving throughput Efficient management of attention key and value memory with PagedAttention Continuous batching of incoming requests Fast model execution with CUDA/HIP graph Quantizations: GPTQ, AWQ, AutoRound, INT4, INT8, and FP8 Optimized CUDA kernels, including integration with FlashAttention and FlashInfer Speculative decoding Chunked prefill urls: - https://github.com/vllm-project/vllm tags: - text-to-text - multimodal - GPTQ - AWQ - AutoRound - INT4 - INT8 - FP8 capabilities: amd: rocm-vllm cpu: cpu-vllm intel: intel-vllm metal: metal-vllm nvidia: cuda12-vllm nvidia-cuda-12: cuda12-vllm nvidia-cuda-13: cuda13-vllm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-vllm mirrors: - localai/localai-backends:master-gpu-intel-vllm - name: cpu-vllm-development alias: vllm license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM is a fast and easy-to-use library for LLM inference and serving. Originally developed in the Sky Computing Lab at UC Berkeley, vLLM has evolved into a community-driven project with contributions from both academia and industry. vLLM is fast with: State-of-the-art serving throughput Efficient management of attention key and value memory with PagedAttention Continuous batching of incoming requests Fast model execution with CUDA/HIP graph Quantizations: GPTQ, AWQ, AutoRound, INT4, INT8, and FP8 Optimized CUDA kernels, including integration with FlashAttention and FlashInfer Speculative decoding Chunked prefill urls: - https://github.com/vllm-project/vllm tags: - text-to-text - multimodal - GPTQ - AWQ - AutoRound - INT4 - INT8 - FP8 capabilities: amd: rocm-vllm cpu: cpu-vllm intel: intel-vllm metal: metal-vllm nvidia: cuda12-vllm nvidia-cuda-12: cuda12-vllm nvidia-cuda-13: cuda13-vllm nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm uri: quay.io/go-skynet/local-ai-backends:master-cpu-vllm mirrors: - localai/localai-backends:master-cpu-vllm - name: sglang-development alias: sglang license: apache-2.0 icon: https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png description: | SGLang is a fast serving framework for large language models and vision language models. It co-designs the backend runtime (RadixAttention, continuous batching, structured decoding) and the frontend language to make interaction with models faster and more controllable. Features include fast backend runtime, flexible frontend language, extensive model support, and an active community. urls: - https://github.com/sgl-project/sglang tags: - text-to-text - multimodal capabilities: amd: rocm-sglang-development cpu: cpu-sglang-development intel: intel-sglang-development nvidia: cuda12-sglang-development nvidia-cuda-12: cuda12-sglang-development nvidia-cuda-13: cuda13-sglang-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sglang-development - name: cuda12-sglang alias: sglang license: apache-2.0 icon: https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png description: | SGLang is a fast serving framework for large language models and vision language models. It co-designs the backend runtime (RadixAttention, continuous batching, structured decoding) and the frontend language to make interaction with models faster and more controllable. Features include fast backend runtime, flexible frontend language, extensive model support, and an active community. urls: - https://github.com/sgl-project/sglang tags: - text-to-text - multimodal capabilities: amd: rocm-sglang cpu: cpu-sglang intel: intel-sglang nvidia: cuda12-sglang nvidia-cuda-12: cuda12-sglang nvidia-cuda-13: cuda13-sglang nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sglang uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-sglang mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-sglang - name: cuda13-sglang alias: sglang license: apache-2.0 icon: https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png description: | SGLang is a fast serving framework for large language models and vision language models. It co-designs the backend runtime (RadixAttention, continuous batching, structured decoding) and the frontend language to make interaction with models faster and more controllable. Features include fast backend runtime, flexible frontend language, extensive model support, and an active community. urls: - https://github.com/sgl-project/sglang tags: - text-to-text - multimodal capabilities: amd: rocm-sglang cpu: cpu-sglang intel: intel-sglang nvidia: cuda12-sglang nvidia-cuda-12: cuda12-sglang nvidia-cuda-13: cuda13-sglang nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sglang uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-sglang mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-sglang - name: cuda13-nvidia-l4t-arm64-sglang alias: sglang license: apache-2.0 icon: https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png description: | SGLang is a fast serving framework for large language models and vision language models. It co-designs the backend runtime (RadixAttention, continuous batching, structured decoding) and the frontend language to make interaction with models faster and more controllable. Features include fast backend runtime, flexible frontend language, extensive model support, and an active community. urls: - https://github.com/sgl-project/sglang tags: - text-to-text - multimodal capabilities: amd: rocm-sglang cpu: cpu-sglang intel: intel-sglang nvidia: cuda12-sglang nvidia-cuda-12: cuda12-sglang nvidia-cuda-13: cuda13-sglang nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sglang uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-sglang mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-sglang - name: rocm-sglang alias: sglang license: apache-2.0 icon: https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png description: | SGLang is a fast serving framework for large language models and vision language models. It co-designs the backend runtime (RadixAttention, continuous batching, structured decoding) and the frontend language to make interaction with models faster and more controllable. Features include fast backend runtime, flexible frontend language, extensive model support, and an active community. urls: - https://github.com/sgl-project/sglang tags: - text-to-text - multimodal capabilities: amd: rocm-sglang cpu: cpu-sglang intel: intel-sglang nvidia: cuda12-sglang nvidia-cuda-12: cuda12-sglang nvidia-cuda-13: cuda13-sglang nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sglang uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-sglang mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-sglang - name: intel-sglang alias: sglang license: apache-2.0 icon: https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png description: | SGLang is a fast serving framework for large language models and vision language models. It co-designs the backend runtime (RadixAttention, continuous batching, structured decoding) and the frontend language to make interaction with models faster and more controllable. Features include fast backend runtime, flexible frontend language, extensive model support, and an active community. urls: - https://github.com/sgl-project/sglang tags: - text-to-text - multimodal capabilities: amd: rocm-sglang cpu: cpu-sglang intel: intel-sglang nvidia: cuda12-sglang nvidia-cuda-12: cuda12-sglang nvidia-cuda-13: cuda13-sglang nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sglang uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sglang mirrors: - localai/localai-backends:latest-gpu-intel-sglang - name: cpu-sglang alias: sglang license: apache-2.0 icon: https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png description: | SGLang is a fast serving framework for large language models and vision language models. It co-designs the backend runtime (RadixAttention, continuous batching, structured decoding) and the frontend language to make interaction with models faster and more controllable. Features include fast backend runtime, flexible frontend language, extensive model support, and an active community. urls: - https://github.com/sgl-project/sglang tags: - text-to-text - multimodal capabilities: amd: rocm-sglang cpu: cpu-sglang intel: intel-sglang nvidia: cuda12-sglang nvidia-cuda-12: cuda12-sglang nvidia-cuda-13: cuda13-sglang nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sglang uri: quay.io/go-skynet/local-ai-backends:latest-cpu-sglang mirrors: - localai/localai-backends:latest-cpu-sglang - name: cuda12-sglang-development alias: sglang license: apache-2.0 icon: https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png description: | SGLang is a fast serving framework for large language models and vision language models. It co-designs the backend runtime (RadixAttention, continuous batching, structured decoding) and the frontend language to make interaction with models faster and more controllable. Features include fast backend runtime, flexible frontend language, extensive model support, and an active community. urls: - https://github.com/sgl-project/sglang tags: - text-to-text - multimodal capabilities: amd: rocm-sglang cpu: cpu-sglang intel: intel-sglang nvidia: cuda12-sglang nvidia-cuda-12: cuda12-sglang nvidia-cuda-13: cuda13-sglang nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sglang uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-sglang mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-sglang - name: cuda13-sglang-development alias: sglang license: apache-2.0 icon: https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png description: | SGLang is a fast serving framework for large language models and vision language models. It co-designs the backend runtime (RadixAttention, continuous batching, structured decoding) and the frontend language to make interaction with models faster and more controllable. Features include fast backend runtime, flexible frontend language, extensive model support, and an active community. urls: - https://github.com/sgl-project/sglang tags: - text-to-text - multimodal capabilities: amd: rocm-sglang cpu: cpu-sglang intel: intel-sglang nvidia: cuda12-sglang nvidia-cuda-12: cuda12-sglang nvidia-cuda-13: cuda13-sglang nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sglang uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-sglang mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-sglang - name: cuda13-nvidia-l4t-arm64-sglang-development alias: sglang license: apache-2.0 icon: https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png description: | SGLang is a fast serving framework for large language models and vision language models. It co-designs the backend runtime (RadixAttention, continuous batching, structured decoding) and the frontend language to make interaction with models faster and more controllable. Features include fast backend runtime, flexible frontend language, extensive model support, and an active community. urls: - https://github.com/sgl-project/sglang tags: - text-to-text - multimodal capabilities: amd: rocm-sglang cpu: cpu-sglang intel: intel-sglang nvidia: cuda12-sglang nvidia-cuda-12: cuda12-sglang nvidia-cuda-13: cuda13-sglang nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sglang uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-sglang mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-sglang - name: rocm-sglang-development alias: sglang license: apache-2.0 icon: https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png description: | SGLang is a fast serving framework for large language models and vision language models. It co-designs the backend runtime (RadixAttention, continuous batching, structured decoding) and the frontend language to make interaction with models faster and more controllable. Features include fast backend runtime, flexible frontend language, extensive model support, and an active community. urls: - https://github.com/sgl-project/sglang tags: - text-to-text - multimodal capabilities: amd: rocm-sglang cpu: cpu-sglang intel: intel-sglang nvidia: cuda12-sglang nvidia-cuda-12: cuda12-sglang nvidia-cuda-13: cuda13-sglang nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sglang uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-sglang mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-sglang - name: intel-sglang-development alias: sglang license: apache-2.0 icon: https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png description: | SGLang is a fast serving framework for large language models and vision language models. It co-designs the backend runtime (RadixAttention, continuous batching, structured decoding) and the frontend language to make interaction with models faster and more controllable. Features include fast backend runtime, flexible frontend language, extensive model support, and an active community. urls: - https://github.com/sgl-project/sglang tags: - text-to-text - multimodal capabilities: amd: rocm-sglang cpu: cpu-sglang intel: intel-sglang nvidia: cuda12-sglang nvidia-cuda-12: cuda12-sglang nvidia-cuda-13: cuda13-sglang nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sglang uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sglang mirrors: - localai/localai-backends:master-gpu-intel-sglang - name: cpu-sglang-development alias: sglang license: apache-2.0 icon: https://raw.githubusercontent.com/sgl-project/sglang/main/assets/logo.png description: | SGLang is a fast serving framework for large language models and vision language models. It co-designs the backend runtime (RadixAttention, continuous batching, structured decoding) and the frontend language to make interaction with models faster and more controllable. Features include fast backend runtime, flexible frontend language, extensive model support, and an active community. urls: - https://github.com/sgl-project/sglang tags: - text-to-text - multimodal capabilities: amd: rocm-sglang cpu: cpu-sglang intel: intel-sglang nvidia: cuda12-sglang nvidia-cuda-12: cuda12-sglang nvidia-cuda-13: cuda13-sglang nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sglang uri: quay.io/go-skynet/local-ai-backends:master-cpu-sglang mirrors: - localai/localai-backends:master-cpu-sglang - name: vllm-omni-development alias: vllm-omni license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM-Omni is a unified interface for multimodal generation with vLLM. It supports image generation (text-to-image, image editing), video generation (text-to-video, image-to-video), text generation with multimodal inputs, and text-to-speech generation. Only supports NVIDIA (CUDA) and ROCm platforms. urls: - https://github.com/vllm-project/vllm-omni tags: - text-to-image - image-generation - text-to-video - video-generation - text-to-speech - TTS - multimodal - LLM capabilities: amd: rocm-vllm-omni-development nvidia: cuda12-vllm-omni-development nvidia-cuda-12: cuda12-vllm-omni-development nvidia-cuda-13: cuda13-vllm-omni-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm-omni-development - name: cuda12-vllm-omni alias: vllm-omni license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM-Omni is a unified interface for multimodal generation with vLLM. It supports image generation (text-to-image, image editing), video generation (text-to-video, image-to-video), text generation with multimodal inputs, and text-to-speech generation. Only supports NVIDIA (CUDA) and ROCm platforms. urls: - https://github.com/vllm-project/vllm-omni tags: - text-to-image - image-generation - text-to-video - video-generation - text-to-speech - TTS - multimodal - LLM capabilities: amd: rocm-vllm-omni nvidia: cuda12-vllm-omni nvidia-cuda-12: cuda12-vllm-omni nvidia-cuda-13: cuda13-vllm-omni nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm-omni uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-vllm-omni mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-vllm-omni - name: cuda13-vllm-omni alias: vllm-omni license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM-Omni is a unified interface for multimodal generation with vLLM. It supports image generation (text-to-image, image editing), video generation (text-to-video, image-to-video), text generation with multimodal inputs, and text-to-speech generation. Only supports NVIDIA (CUDA) and ROCm platforms. urls: - https://github.com/vllm-project/vllm-omni tags: - text-to-image - image-generation - text-to-video - video-generation - text-to-speech - TTS - multimodal - LLM capabilities: amd: rocm-vllm-omni nvidia: cuda12-vllm-omni nvidia-cuda-12: cuda12-vllm-omni nvidia-cuda-13: cuda13-vllm-omni nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm-omni uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-vllm-omni mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-vllm-omni - name: cuda13-nvidia-l4t-arm64-vllm-omni alias: vllm-omni license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM-Omni is a unified interface for multimodal generation with vLLM. It supports image generation (text-to-image, image editing), video generation (text-to-video, image-to-video), text generation with multimodal inputs, and text-to-speech generation. Only supports NVIDIA (CUDA) and ROCm platforms. urls: - https://github.com/vllm-project/vllm-omni tags: - text-to-image - image-generation - text-to-video - video-generation - text-to-speech - TTS - multimodal - LLM capabilities: amd: rocm-vllm-omni nvidia: cuda12-vllm-omni nvidia-cuda-12: cuda12-vllm-omni nvidia-cuda-13: cuda13-vllm-omni nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm-omni uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-vllm-omni mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-vllm-omni - name: rocm-vllm-omni alias: vllm-omni license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM-Omni is a unified interface for multimodal generation with vLLM. It supports image generation (text-to-image, image editing), video generation (text-to-video, image-to-video), text generation with multimodal inputs, and text-to-speech generation. Only supports NVIDIA (CUDA) and ROCm platforms. urls: - https://github.com/vllm-project/vllm-omni tags: - text-to-image - image-generation - text-to-video - video-generation - text-to-speech - TTS - multimodal - LLM capabilities: amd: rocm-vllm-omni nvidia: cuda12-vllm-omni nvidia-cuda-12: cuda12-vllm-omni nvidia-cuda-13: cuda13-vllm-omni nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm-omni uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-vllm-omni mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-vllm-omni - name: cuda12-vllm-omni-development alias: vllm-omni license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM-Omni is a unified interface for multimodal generation with vLLM. It supports image generation (text-to-image, image editing), video generation (text-to-video, image-to-video), text generation with multimodal inputs, and text-to-speech generation. Only supports NVIDIA (CUDA) and ROCm platforms. urls: - https://github.com/vllm-project/vllm-omni tags: - text-to-image - image-generation - text-to-video - video-generation - text-to-speech - TTS - multimodal - LLM capabilities: amd: rocm-vllm-omni nvidia: cuda12-vllm-omni nvidia-cuda-12: cuda12-vllm-omni nvidia-cuda-13: cuda13-vllm-omni nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm-omni uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-vllm-omni mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-vllm-omni - name: cuda13-vllm-omni-development alias: vllm-omni license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM-Omni is a unified interface for multimodal generation with vLLM. It supports image generation (text-to-image, image editing), video generation (text-to-video, image-to-video), text generation with multimodal inputs, and text-to-speech generation. Only supports NVIDIA (CUDA) and ROCm platforms. urls: - https://github.com/vllm-project/vllm-omni tags: - text-to-image - image-generation - text-to-video - video-generation - text-to-speech - TTS - multimodal - LLM capabilities: amd: rocm-vllm-omni nvidia: cuda12-vllm-omni nvidia-cuda-12: cuda12-vllm-omni nvidia-cuda-13: cuda13-vllm-omni nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm-omni uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-vllm-omni mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-vllm-omni - name: cuda13-nvidia-l4t-arm64-vllm-omni-development alias: vllm-omni license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM-Omni is a unified interface for multimodal generation with vLLM. It supports image generation (text-to-image, image editing), video generation (text-to-video, image-to-video), text generation with multimodal inputs, and text-to-speech generation. Only supports NVIDIA (CUDA) and ROCm platforms. urls: - https://github.com/vllm-project/vllm-omni tags: - text-to-image - image-generation - text-to-video - video-generation - text-to-speech - TTS - multimodal - LLM capabilities: amd: rocm-vllm-omni nvidia: cuda12-vllm-omni nvidia-cuda-12: cuda12-vllm-omni nvidia-cuda-13: cuda13-vllm-omni nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm-omni uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-vllm-omni mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-vllm-omni - name: rocm-vllm-omni-development alias: vllm-omni license: apache-2.0 icon: https://raw.githubusercontent.com/vllm-project/vllm/main/docs/assets/logos/vllm-logo-text-dark.png description: | vLLM-Omni is a unified interface for multimodal generation with vLLM. It supports image generation (text-to-image, image editing), video generation (text-to-video, image-to-video), text generation with multimodal inputs, and text-to-speech generation. Only supports NVIDIA (CUDA) and ROCm platforms. urls: - https://github.com/vllm-project/vllm-omni tags: - text-to-image - image-generation - text-to-video - video-generation - text-to-speech - TTS - multimodal - LLM capabilities: amd: rocm-vllm-omni nvidia: cuda12-vllm-omni nvidia-cuda-12: cuda12-vllm-omni nvidia-cuda-13: cuda13-vllm-omni nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vllm-omni uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-vllm-omni mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-vllm-omni - name: longcat-video-development alias: longcat-video license: mit icon: https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/main/assets/longcat-video_logo.svg description: | LongCat-Video generation for text, image, and audio-conditioned avatars. Supports LongCat-Video and LongCat-Video-Avatar-1.5, including multi-segment talking-head continuation and an SDPA path for NVIDIA Blackwell ARM64 systems. Requires Linux with an NVIDIA CUDA GPU; CPU, ROCm, and macOS are unsupported. urls: - https://github.com/meituan-longcat/LongCat-Video tags: - text-to-video - image-to-video - audio-to-video - avatar-generation - video-generation - CUDA capabilities: nvidia: cuda12-longcat-video-development nvidia-cuda-12: cuda12-longcat-video-development nvidia-cuda-13: cuda13-longcat-video-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-longcat-video-development - name: cuda12-longcat-video alias: longcat-video license: mit icon: https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/main/assets/longcat-video_logo.svg description: | LongCat-Video generation for text, image, and audio-conditioned avatars. Supports LongCat-Video and LongCat-Video-Avatar-1.5, including multi-segment talking-head continuation and an SDPA path for NVIDIA Blackwell ARM64 systems. Requires Linux with an NVIDIA CUDA GPU; CPU, ROCm, and macOS are unsupported. urls: - https://github.com/meituan-longcat/LongCat-Video tags: - text-to-video - image-to-video - audio-to-video - avatar-generation - video-generation - CUDA capabilities: nvidia: cuda12-longcat-video nvidia-cuda-12: cuda12-longcat-video nvidia-cuda-13: cuda13-longcat-video nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-longcat-video uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-longcat-video mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-longcat-video - name: cuda13-longcat-video alias: longcat-video license: mit icon: https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/main/assets/longcat-video_logo.svg description: | LongCat-Video generation for text, image, and audio-conditioned avatars. Supports LongCat-Video and LongCat-Video-Avatar-1.5, including multi-segment talking-head continuation and an SDPA path for NVIDIA Blackwell ARM64 systems. Requires Linux with an NVIDIA CUDA GPU; CPU, ROCm, and macOS are unsupported. urls: - https://github.com/meituan-longcat/LongCat-Video tags: - text-to-video - image-to-video - audio-to-video - avatar-generation - video-generation - CUDA capabilities: nvidia: cuda12-longcat-video nvidia-cuda-12: cuda12-longcat-video nvidia-cuda-13: cuda13-longcat-video nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-longcat-video uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-longcat-video mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-longcat-video - name: cuda13-nvidia-l4t-arm64-longcat-video alias: longcat-video license: mit icon: https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/main/assets/longcat-video_logo.svg description: | LongCat-Video generation for text, image, and audio-conditioned avatars. Supports LongCat-Video and LongCat-Video-Avatar-1.5, including multi-segment talking-head continuation and an SDPA path for NVIDIA Blackwell ARM64 systems. Requires Linux with an NVIDIA CUDA GPU; CPU, ROCm, and macOS are unsupported. urls: - https://github.com/meituan-longcat/LongCat-Video tags: - text-to-video - image-to-video - audio-to-video - avatar-generation - video-generation - CUDA capabilities: nvidia: cuda12-longcat-video nvidia-cuda-12: cuda12-longcat-video nvidia-cuda-13: cuda13-longcat-video nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-longcat-video uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-longcat-video mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-longcat-video - name: cuda12-longcat-video-development alias: longcat-video license: mit icon: https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/main/assets/longcat-video_logo.svg description: | LongCat-Video generation for text, image, and audio-conditioned avatars. Supports LongCat-Video and LongCat-Video-Avatar-1.5, including multi-segment talking-head continuation and an SDPA path for NVIDIA Blackwell ARM64 systems. Requires Linux with an NVIDIA CUDA GPU; CPU, ROCm, and macOS are unsupported. urls: - https://github.com/meituan-longcat/LongCat-Video tags: - text-to-video - image-to-video - audio-to-video - avatar-generation - video-generation - CUDA capabilities: nvidia: cuda12-longcat-video nvidia-cuda-12: cuda12-longcat-video nvidia-cuda-13: cuda13-longcat-video nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-longcat-video uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-longcat-video mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-longcat-video - name: cuda13-longcat-video-development alias: longcat-video license: mit icon: https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/main/assets/longcat-video_logo.svg description: | LongCat-Video generation for text, image, and audio-conditioned avatars. Supports LongCat-Video and LongCat-Video-Avatar-1.5, including multi-segment talking-head continuation and an SDPA path for NVIDIA Blackwell ARM64 systems. Requires Linux with an NVIDIA CUDA GPU; CPU, ROCm, and macOS are unsupported. urls: - https://github.com/meituan-longcat/LongCat-Video tags: - text-to-video - image-to-video - audio-to-video - avatar-generation - video-generation - CUDA capabilities: nvidia: cuda12-longcat-video nvidia-cuda-12: cuda12-longcat-video nvidia-cuda-13: cuda13-longcat-video nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-longcat-video uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-longcat-video mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-longcat-video - name: cuda13-nvidia-l4t-arm64-longcat-video-development alias: longcat-video license: mit icon: https://raw.githubusercontent.com/meituan-longcat/LongCat-Video/main/assets/longcat-video_logo.svg description: | LongCat-Video generation for text, image, and audio-conditioned avatars. Supports LongCat-Video and LongCat-Video-Avatar-1.5, including multi-segment talking-head continuation and an SDPA path for NVIDIA Blackwell ARM64 systems. Requires Linux with an NVIDIA CUDA GPU; CPU, ROCm, and macOS are unsupported. urls: - https://github.com/meituan-longcat/LongCat-Video tags: - text-to-video - image-to-video - audio-to-video - avatar-generation - video-generation - CUDA capabilities: nvidia: cuda12-longcat-video nvidia-cuda-12: cuda12-longcat-video nvidia-cuda-13: cuda13-longcat-video nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-longcat-video uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-longcat-video mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-longcat-video - name: rfdetr-development alias: rfdetr license: apache-2.0 icon: https://avatars.githubusercontent.com/u/53104118?s=200&v=4 description: | RF-DETR is a real-time, transformer-based object detection model architecture developed by Roboflow and released under the Apache 2.0 license. RF-DETR is the first real-time model to exceed 60 AP on the Microsoft COCO benchmark alongside competitive performance at base sizes. It also achieves state-of-the-art performance on RF100-VL, an object detection benchmark that measures model domain adaptability to real world problems. RF-DETR is fastest and most accurate for its size when compared current real-time objection models. RF-DETR is small enough to run on the edge using Inference, making it an ideal model for deployments that need both strong accuracy and real-time performance. urls: - https://github.com/roboflow/rf-detr tags: - object-detection - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr-development intel: intel-rfdetr-development metal: metal-rfdetr-development nvidia: cuda12-rfdetr-development nvidia-cuda-13: cuda13-rfdetr-development nvidia-l4t: nvidia-l4t-arm64-rfdetr-development - name: cuda12-rfdetr alias: rfdetr license: apache-2.0 icon: https://avatars.githubusercontent.com/u/53104118?s=200&v=4 description: | RF-DETR is a real-time, transformer-based object detection model architecture developed by Roboflow and released under the Apache 2.0 license. RF-DETR is the first real-time model to exceed 60 AP on the Microsoft COCO benchmark alongside competitive performance at base sizes. It also achieves state-of-the-art performance on RF100-VL, an object detection benchmark that measures model domain adaptability to real world problems. RF-DETR is fastest and most accurate for its size when compared current real-time objection models. RF-DETR is small enough to run on the edge using Inference, making it an ideal model for deployments that need both strong accuracy and real-time performance. urls: - https://github.com/roboflow/rf-detr tags: - object-detection - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr intel: intel-rfdetr metal: metal-rfdetr nvidia: cuda12-rfdetr nvidia-cuda-12: cuda12-rfdetr nvidia-cuda-13: cuda13-rfdetr nvidia-l4t: nvidia-l4t-arm64-rfdetr nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-rfdetr mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-rfdetr - name: intel-rfdetr alias: rfdetr license: apache-2.0 icon: https://avatars.githubusercontent.com/u/53104118?s=200&v=4 description: | RF-DETR is a real-time, transformer-based object detection model architecture developed by Roboflow and released under the Apache 2.0 license. RF-DETR is the first real-time model to exceed 60 AP on the Microsoft COCO benchmark alongside competitive performance at base sizes. It also achieves state-of-the-art performance on RF100-VL, an object detection benchmark that measures model domain adaptability to real world problems. RF-DETR is fastest and most accurate for its size when compared current real-time objection models. RF-DETR is small enough to run on the edge using Inference, making it an ideal model for deployments that need both strong accuracy and real-time performance. urls: - https://github.com/roboflow/rf-detr tags: - object-detection - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr intel: intel-rfdetr metal: metal-rfdetr nvidia: cuda12-rfdetr nvidia-cuda-12: cuda12-rfdetr nvidia-cuda-13: cuda13-rfdetr nvidia-l4t: nvidia-l4t-arm64-rfdetr nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-rfdetr mirrors: - localai/localai-backends:latest-gpu-intel-rfdetr - name: nvidia-l4t-arm64-rfdetr alias: rfdetr license: apache-2.0 icon: https://avatars.githubusercontent.com/u/53104118?s=200&v=4 description: | RF-DETR is a real-time, transformer-based object detection model architecture developed by Roboflow and released under the Apache 2.0 license. RF-DETR is the first real-time model to exceed 60 AP on the Microsoft COCO benchmark alongside competitive performance at base sizes. It also achieves state-of-the-art performance on RF100-VL, an object detection benchmark that measures model domain adaptability to real world problems. RF-DETR is fastest and most accurate for its size when compared current real-time objection models. RF-DETR is small enough to run on the edge using Inference, making it an ideal model for deployments that need both strong accuracy and real-time performance. urls: - https://github.com/roboflow/rf-detr tags: - object-detection - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr intel: intel-rfdetr metal: metal-rfdetr nvidia: cuda12-rfdetr nvidia-cuda-12: cuda12-rfdetr nvidia-cuda-13: cuda13-rfdetr nvidia-l4t: nvidia-l4t-arm64-rfdetr nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-rfdetr mirrors: - localai/localai-backends:latest-nvidia-l4t-arm64-rfdetr - name: nvidia-l4t-arm64-rfdetr-development alias: rfdetr license: apache-2.0 icon: https://avatars.githubusercontent.com/u/53104118?s=200&v=4 description: | RF-DETR is a real-time, transformer-based object detection model architecture developed by Roboflow and released under the Apache 2.0 license. RF-DETR is the first real-time model to exceed 60 AP on the Microsoft COCO benchmark alongside competitive performance at base sizes. It also achieves state-of-the-art performance on RF100-VL, an object detection benchmark that measures model domain adaptability to real world problems. RF-DETR is fastest and most accurate for its size when compared current real-time objection models. RF-DETR is small enough to run on the edge using Inference, making it an ideal model for deployments that need both strong accuracy and real-time performance. urls: - https://github.com/roboflow/rf-detr tags: - object-detection - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr intel: intel-rfdetr metal: metal-rfdetr nvidia: cuda12-rfdetr nvidia-cuda-12: cuda12-rfdetr nvidia-cuda-13: cuda13-rfdetr nvidia-l4t: nvidia-l4t-arm64-rfdetr nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-rfdetr mirrors: - localai/localai-backends:master-nvidia-l4t-arm64-rfdetr - name: cpu-rfdetr alias: rfdetr license: apache-2.0 icon: https://avatars.githubusercontent.com/u/53104118?s=200&v=4 description: | RF-DETR is a real-time, transformer-based object detection model architecture developed by Roboflow and released under the Apache 2.0 license. RF-DETR is the first real-time model to exceed 60 AP on the Microsoft COCO benchmark alongside competitive performance at base sizes. It also achieves state-of-the-art performance on RF100-VL, an object detection benchmark that measures model domain adaptability to real world problems. RF-DETR is fastest and most accurate for its size when compared current real-time objection models. RF-DETR is small enough to run on the edge using Inference, making it an ideal model for deployments that need both strong accuracy and real-time performance. urls: - https://github.com/roboflow/rf-detr tags: - object-detection - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr intel: intel-rfdetr metal: metal-rfdetr nvidia: cuda12-rfdetr nvidia-cuda-12: cuda12-rfdetr nvidia-cuda-13: cuda13-rfdetr nvidia-l4t: nvidia-l4t-arm64-rfdetr nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr uri: quay.io/go-skynet/local-ai-backends:latest-cpu-rfdetr mirrors: - localai/localai-backends:latest-cpu-rfdetr - name: cuda12-rfdetr-development alias: rfdetr license: apache-2.0 icon: https://avatars.githubusercontent.com/u/53104118?s=200&v=4 description: | RF-DETR is a real-time, transformer-based object detection model architecture developed by Roboflow and released under the Apache 2.0 license. RF-DETR is the first real-time model to exceed 60 AP on the Microsoft COCO benchmark alongside competitive performance at base sizes. It also achieves state-of-the-art performance on RF100-VL, an object detection benchmark that measures model domain adaptability to real world problems. RF-DETR is fastest and most accurate for its size when compared current real-time objection models. RF-DETR is small enough to run on the edge using Inference, making it an ideal model for deployments that need both strong accuracy and real-time performance. urls: - https://github.com/roboflow/rf-detr tags: - object-detection - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr intel: intel-rfdetr metal: metal-rfdetr nvidia: cuda12-rfdetr nvidia-cuda-12: cuda12-rfdetr nvidia-cuda-13: cuda13-rfdetr nvidia-l4t: nvidia-l4t-arm64-rfdetr nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-rfdetr mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-rfdetr - name: intel-rfdetr-development alias: rfdetr license: apache-2.0 icon: https://avatars.githubusercontent.com/u/53104118?s=200&v=4 description: | RF-DETR is a real-time, transformer-based object detection model architecture developed by Roboflow and released under the Apache 2.0 license. RF-DETR is the first real-time model to exceed 60 AP on the Microsoft COCO benchmark alongside competitive performance at base sizes. It also achieves state-of-the-art performance on RF100-VL, an object detection benchmark that measures model domain adaptability to real world problems. RF-DETR is fastest and most accurate for its size when compared current real-time objection models. RF-DETR is small enough to run on the edge using Inference, making it an ideal model for deployments that need both strong accuracy and real-time performance. urls: - https://github.com/roboflow/rf-detr tags: - object-detection - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr intel: intel-rfdetr metal: metal-rfdetr nvidia: cuda12-rfdetr nvidia-cuda-12: cuda12-rfdetr nvidia-cuda-13: cuda13-rfdetr nvidia-l4t: nvidia-l4t-arm64-rfdetr nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-rfdetr mirrors: - localai/localai-backends:master-gpu-intel-rfdetr - name: cpu-rfdetr-development alias: rfdetr license: apache-2.0 icon: https://avatars.githubusercontent.com/u/53104118?s=200&v=4 description: | RF-DETR is a real-time, transformer-based object detection model architecture developed by Roboflow and released under the Apache 2.0 license. RF-DETR is the first real-time model to exceed 60 AP on the Microsoft COCO benchmark alongside competitive performance at base sizes. It also achieves state-of-the-art performance on RF100-VL, an object detection benchmark that measures model domain adaptability to real world problems. RF-DETR is fastest and most accurate for its size when compared current real-time objection models. RF-DETR is small enough to run on the edge using Inference, making it an ideal model for deployments that need both strong accuracy and real-time performance. urls: - https://github.com/roboflow/rf-detr tags: - object-detection - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr intel: intel-rfdetr metal: metal-rfdetr nvidia: cuda12-rfdetr nvidia-cuda-12: cuda12-rfdetr nvidia-cuda-13: cuda13-rfdetr nvidia-l4t: nvidia-l4t-arm64-rfdetr nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr uri: quay.io/go-skynet/local-ai-backends:master-cpu-rfdetr mirrors: - localai/localai-backends:master-cpu-rfdetr - name: cuda13-rfdetr alias: rfdetr license: apache-2.0 icon: https://avatars.githubusercontent.com/u/53104118?s=200&v=4 description: | RF-DETR is a real-time, transformer-based object detection model architecture developed by Roboflow and released under the Apache 2.0 license. RF-DETR is the first real-time model to exceed 60 AP on the Microsoft COCO benchmark alongside competitive performance at base sizes. It also achieves state-of-the-art performance on RF100-VL, an object detection benchmark that measures model domain adaptability to real world problems. RF-DETR is fastest and most accurate for its size when compared current real-time objection models. RF-DETR is small enough to run on the edge using Inference, making it an ideal model for deployments that need both strong accuracy and real-time performance. urls: - https://github.com/roboflow/rf-detr tags: - object-detection - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr intel: intel-rfdetr metal: metal-rfdetr nvidia: cuda12-rfdetr nvidia-cuda-12: cuda12-rfdetr nvidia-cuda-13: cuda13-rfdetr nvidia-l4t: nvidia-l4t-arm64-rfdetr nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-rfdetr mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-rfdetr - name: cuda13-rfdetr-development alias: rfdetr license: apache-2.0 icon: https://avatars.githubusercontent.com/u/53104118?s=200&v=4 description: | RF-DETR is a real-time, transformer-based object detection model architecture developed by Roboflow and released under the Apache 2.0 license. RF-DETR is the first real-time model to exceed 60 AP on the Microsoft COCO benchmark alongside competitive performance at base sizes. It also achieves state-of-the-art performance on RF100-VL, an object detection benchmark that measures model domain adaptability to real world problems. RF-DETR is fastest and most accurate for its size when compared current real-time objection models. RF-DETR is small enough to run on the edge using Inference, making it an ideal model for deployments that need both strong accuracy and real-time performance. urls: - https://github.com/roboflow/rf-detr tags: - object-detection - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr intel: intel-rfdetr metal: metal-rfdetr nvidia: cuda12-rfdetr nvidia-cuda-12: cuda12-rfdetr nvidia-cuda-13: cuda13-rfdetr nvidia-l4t: nvidia-l4t-arm64-rfdetr nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-rfdetr mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-rfdetr - name: metal-rfdetr alias: rfdetr license: apache-2.0 icon: https://avatars.githubusercontent.com/u/53104118?s=200&v=4 description: | RF-DETR is a real-time, transformer-based object detection model architecture developed by Roboflow and released under the Apache 2.0 license. RF-DETR is the first real-time model to exceed 60 AP on the Microsoft COCO benchmark alongside competitive performance at base sizes. It also achieves state-of-the-art performance on RF100-VL, an object detection benchmark that measures model domain adaptability to real world problems. RF-DETR is fastest and most accurate for its size when compared current real-time objection models. RF-DETR is small enough to run on the edge using Inference, making it an ideal model for deployments that need both strong accuracy and real-time performance. urls: - https://github.com/roboflow/rf-detr tags: - object-detection - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr intel: intel-rfdetr metal: metal-rfdetr nvidia: cuda12-rfdetr nvidia-cuda-12: cuda12-rfdetr nvidia-cuda-13: cuda13-rfdetr nvidia-l4t: nvidia-l4t-arm64-rfdetr nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-rfdetr mirrors: - localai/localai-backends:latest-metal-darwin-arm64-rfdetr - name: metal-rfdetr-development alias: rfdetr license: apache-2.0 icon: https://avatars.githubusercontent.com/u/53104118?s=200&v=4 description: | RF-DETR is a real-time, transformer-based object detection model architecture developed by Roboflow and released under the Apache 2.0 license. RF-DETR is the first real-time model to exceed 60 AP on the Microsoft COCO benchmark alongside competitive performance at base sizes. It also achieves state-of-the-art performance on RF100-VL, an object detection benchmark that measures model domain adaptability to real world problems. RF-DETR is fastest and most accurate for its size when compared current real-time objection models. RF-DETR is small enough to run on the edge using Inference, making it an ideal model for deployments that need both strong accuracy and real-time performance. urls: - https://github.com/roboflow/rf-detr tags: - object-detection - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr intel: intel-rfdetr metal: metal-rfdetr nvidia: cuda12-rfdetr nvidia-cuda-12: cuda12-rfdetr nvidia-cuda-13: cuda13-rfdetr nvidia-l4t: nvidia-l4t-arm64-rfdetr nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-rfdetr mirrors: - localai/localai-backends:master-metal-darwin-arm64-rfdetr - name: sam3-cpp-development alias: sam3-cpp license: mit description: | Segment Anything Model (SAM 3/2/EdgeTAM) in C/C++ using GGML. Supports text-prompted and point/box-prompted image segmentation. urls: - https://github.com/PABannier/sam3.cpp tags: - image-segmentation - object-detection - sam3 - gpu - cpu capabilities: default: cpu-sam3-cpp-development intel: intel-sycl-f32-sam3-cpp-development metal: metal-sam3-cpp-development nvidia: cuda12-sam3-cpp-development nvidia-cuda-12: cuda12-sam3-cpp-development nvidia-cuda-13: cuda13-sam3-cpp-development nvidia-l4t: nvidia-l4t-arm64-sam3-cpp-development nvidia-l4t-cuda-12: nvidia-l4t-arm64-sam3-cpp-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sam3-cpp-development vulkan: vulkan-sam3-cpp-development - name: cpu-sam3-cpp alias: sam3-cpp license: mit description: | Segment Anything Model (SAM 3/2/EdgeTAM) in C/C++ using GGML. Supports text-prompted and point/box-prompted image segmentation. urls: - https://github.com/PABannier/sam3.cpp tags: - image-segmentation - object-detection - sam3 - gpu - cpu capabilities: default: cpu-sam3-cpp intel: intel-sycl-f32-sam3-cpp metal: metal-sam3-cpp nvidia: cuda12-sam3-cpp nvidia-cuda-12: cuda12-sam3-cpp nvidia-cuda-13: cuda13-sam3-cpp nvidia-l4t: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sam3-cpp vulkan: vulkan-sam3-cpp uri: quay.io/go-skynet/local-ai-backends:latest-cpu-sam3-cpp mirrors: - localai/localai-backends:latest-cpu-sam3-cpp - name: cpu-sam3-cpp-development alias: sam3-cpp license: mit description: | Segment Anything Model (SAM 3/2/EdgeTAM) in C/C++ using GGML. Supports text-prompted and point/box-prompted image segmentation. urls: - https://github.com/PABannier/sam3.cpp tags: - image-segmentation - object-detection - sam3 - gpu - cpu capabilities: default: cpu-sam3-cpp intel: intel-sycl-f32-sam3-cpp metal: metal-sam3-cpp nvidia: cuda12-sam3-cpp nvidia-cuda-12: cuda12-sam3-cpp nvidia-cuda-13: cuda13-sam3-cpp nvidia-l4t: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sam3-cpp vulkan: vulkan-sam3-cpp uri: quay.io/go-skynet/local-ai-backends:master-cpu-sam3-cpp mirrors: - localai/localai-backends:master-cpu-sam3-cpp - name: metal-sam3-cpp alias: sam3-cpp license: mit description: | Segment Anything Model (SAM 3/2/EdgeTAM) in C/C++ using GGML. Supports text-prompted and point/box-prompted image segmentation. urls: - https://github.com/PABannier/sam3.cpp tags: - image-segmentation - object-detection - sam3 - gpu - cpu capabilities: default: cpu-sam3-cpp intel: intel-sycl-f32-sam3-cpp metal: metal-sam3-cpp nvidia: cuda12-sam3-cpp nvidia-cuda-12: cuda12-sam3-cpp nvidia-cuda-13: cuda13-sam3-cpp nvidia-l4t: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sam3-cpp vulkan: vulkan-sam3-cpp uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-sam3-cpp mirrors: - localai/localai-backends:latest-metal-darwin-arm64-sam3-cpp - name: metal-sam3-cpp-development alias: sam3-cpp license: mit description: | Segment Anything Model (SAM 3/2/EdgeTAM) in C/C++ using GGML. Supports text-prompted and point/box-prompted image segmentation. urls: - https://github.com/PABannier/sam3.cpp tags: - image-segmentation - object-detection - sam3 - gpu - cpu capabilities: default: cpu-sam3-cpp intel: intel-sycl-f32-sam3-cpp metal: metal-sam3-cpp nvidia: cuda12-sam3-cpp nvidia-cuda-12: cuda12-sam3-cpp nvidia-cuda-13: cuda13-sam3-cpp nvidia-l4t: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sam3-cpp vulkan: vulkan-sam3-cpp uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-sam3-cpp mirrors: - localai/localai-backends:master-metal-darwin-arm64-sam3-cpp - name: cuda12-sam3-cpp alias: sam3-cpp license: mit description: | Segment Anything Model (SAM 3/2/EdgeTAM) in C/C++ using GGML. Supports text-prompted and point/box-prompted image segmentation. urls: - https://github.com/PABannier/sam3.cpp tags: - image-segmentation - object-detection - sam3 - gpu - cpu capabilities: default: cpu-sam3-cpp intel: intel-sycl-f32-sam3-cpp metal: metal-sam3-cpp nvidia: cuda12-sam3-cpp nvidia-cuda-12: cuda12-sam3-cpp nvidia-cuda-13: cuda13-sam3-cpp nvidia-l4t: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sam3-cpp vulkan: vulkan-sam3-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-sam3-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-sam3-cpp - name: cuda12-sam3-cpp-development alias: sam3-cpp license: mit description: | Segment Anything Model (SAM 3/2/EdgeTAM) in C/C++ using GGML. Supports text-prompted and point/box-prompted image segmentation. urls: - https://github.com/PABannier/sam3.cpp tags: - image-segmentation - object-detection - sam3 - gpu - cpu capabilities: default: cpu-sam3-cpp intel: intel-sycl-f32-sam3-cpp metal: metal-sam3-cpp nvidia: cuda12-sam3-cpp nvidia-cuda-12: cuda12-sam3-cpp nvidia-cuda-13: cuda13-sam3-cpp nvidia-l4t: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sam3-cpp vulkan: vulkan-sam3-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-sam3-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-sam3-cpp - name: cuda13-sam3-cpp alias: sam3-cpp license: mit description: | Segment Anything Model (SAM 3/2/EdgeTAM) in C/C++ using GGML. Supports text-prompted and point/box-prompted image segmentation. urls: - https://github.com/PABannier/sam3.cpp tags: - image-segmentation - object-detection - sam3 - gpu - cpu capabilities: default: cpu-sam3-cpp intel: intel-sycl-f32-sam3-cpp metal: metal-sam3-cpp nvidia: cuda12-sam3-cpp nvidia-cuda-12: cuda12-sam3-cpp nvidia-cuda-13: cuda13-sam3-cpp nvidia-l4t: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sam3-cpp vulkan: vulkan-sam3-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-sam3-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-sam3-cpp - name: cuda13-sam3-cpp-development alias: sam3-cpp license: mit description: | Segment Anything Model (SAM 3/2/EdgeTAM) in C/C++ using GGML. Supports text-prompted and point/box-prompted image segmentation. urls: - https://github.com/PABannier/sam3.cpp tags: - image-segmentation - object-detection - sam3 - gpu - cpu capabilities: default: cpu-sam3-cpp intel: intel-sycl-f32-sam3-cpp metal: metal-sam3-cpp nvidia: cuda12-sam3-cpp nvidia-cuda-12: cuda12-sam3-cpp nvidia-cuda-13: cuda13-sam3-cpp nvidia-l4t: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sam3-cpp vulkan: vulkan-sam3-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-sam3-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-sam3-cpp - name: nvidia-l4t-arm64-sam3-cpp alias: sam3-cpp license: mit description: | Segment Anything Model (SAM 3/2/EdgeTAM) in C/C++ using GGML. Supports text-prompted and point/box-prompted image segmentation. urls: - https://github.com/PABannier/sam3.cpp tags: - image-segmentation - object-detection - sam3 - gpu - cpu capabilities: default: cpu-sam3-cpp intel: intel-sycl-f32-sam3-cpp metal: metal-sam3-cpp nvidia: cuda12-sam3-cpp nvidia-cuda-12: cuda12-sam3-cpp nvidia-cuda-13: cuda13-sam3-cpp nvidia-l4t: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sam3-cpp vulkan: vulkan-sam3-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-sam3-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-arm64-sam3-cpp - name: nvidia-l4t-arm64-sam3-cpp-development alias: sam3-cpp license: mit description: | Segment Anything Model (SAM 3/2/EdgeTAM) in C/C++ using GGML. Supports text-prompted and point/box-prompted image segmentation. urls: - https://github.com/PABannier/sam3.cpp tags: - image-segmentation - object-detection - sam3 - gpu - cpu capabilities: default: cpu-sam3-cpp intel: intel-sycl-f32-sam3-cpp metal: metal-sam3-cpp nvidia: cuda12-sam3-cpp nvidia-cuda-12: cuda12-sam3-cpp nvidia-cuda-13: cuda13-sam3-cpp nvidia-l4t: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sam3-cpp vulkan: vulkan-sam3-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-sam3-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-arm64-sam3-cpp - name: cuda13-nvidia-l4t-arm64-sam3-cpp alias: sam3-cpp license: mit description: | Segment Anything Model (SAM 3/2/EdgeTAM) in C/C++ using GGML. Supports text-prompted and point/box-prompted image segmentation. urls: - https://github.com/PABannier/sam3.cpp tags: - image-segmentation - object-detection - sam3 - gpu - cpu capabilities: default: cpu-sam3-cpp intel: intel-sycl-f32-sam3-cpp metal: metal-sam3-cpp nvidia: cuda12-sam3-cpp nvidia-cuda-12: cuda12-sam3-cpp nvidia-cuda-13: cuda13-sam3-cpp nvidia-l4t: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sam3-cpp vulkan: vulkan-sam3-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-sam3-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-sam3-cpp - name: cuda13-nvidia-l4t-arm64-sam3-cpp-development alias: sam3-cpp license: mit description: | Segment Anything Model (SAM 3/2/EdgeTAM) in C/C++ using GGML. Supports text-prompted and point/box-prompted image segmentation. urls: - https://github.com/PABannier/sam3.cpp tags: - image-segmentation - object-detection - sam3 - gpu - cpu capabilities: default: cpu-sam3-cpp intel: intel-sycl-f32-sam3-cpp metal: metal-sam3-cpp nvidia: cuda12-sam3-cpp nvidia-cuda-12: cuda12-sam3-cpp nvidia-cuda-13: cuda13-sam3-cpp nvidia-l4t: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sam3-cpp vulkan: vulkan-sam3-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-sam3-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-sam3-cpp - name: intel-sycl-f32-sam3-cpp alias: sam3-cpp license: mit description: | Segment Anything Model (SAM 3/2/EdgeTAM) in C/C++ using GGML. Supports text-prompted and point/box-prompted image segmentation. urls: - https://github.com/PABannier/sam3.cpp tags: - image-segmentation - object-detection - sam3 - gpu - cpu capabilities: default: cpu-sam3-cpp intel: intel-sycl-f32-sam3-cpp metal: metal-sam3-cpp nvidia: cuda12-sam3-cpp nvidia-cuda-12: cuda12-sam3-cpp nvidia-cuda-13: cuda13-sam3-cpp nvidia-l4t: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sam3-cpp vulkan: vulkan-sam3-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-sam3-cpp mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f32-sam3-cpp - name: intel-sycl-f32-sam3-cpp-development alias: sam3-cpp license: mit description: | Segment Anything Model (SAM 3/2/EdgeTAM) in C/C++ using GGML. Supports text-prompted and point/box-prompted image segmentation. urls: - https://github.com/PABannier/sam3.cpp tags: - image-segmentation - object-detection - sam3 - gpu - cpu capabilities: default: cpu-sam3-cpp intel: intel-sycl-f32-sam3-cpp metal: metal-sam3-cpp nvidia: cuda12-sam3-cpp nvidia-cuda-12: cuda12-sam3-cpp nvidia-cuda-13: cuda13-sam3-cpp nvidia-l4t: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sam3-cpp vulkan: vulkan-sam3-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-sam3-cpp mirrors: - localai/localai-backends:master-gpu-intel-sycl-f32-sam3-cpp - name: vulkan-sam3-cpp alias: sam3-cpp license: mit description: | Segment Anything Model (SAM 3/2/EdgeTAM) in C/C++ using GGML. Supports text-prompted and point/box-prompted image segmentation. urls: - https://github.com/PABannier/sam3.cpp tags: - image-segmentation - object-detection - sam3 - gpu - cpu capabilities: default: cpu-sam3-cpp intel: intel-sycl-f32-sam3-cpp metal: metal-sam3-cpp nvidia: cuda12-sam3-cpp nvidia-cuda-12: cuda12-sam3-cpp nvidia-cuda-13: cuda13-sam3-cpp nvidia-l4t: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sam3-cpp vulkan: vulkan-sam3-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-sam3-cpp mirrors: - localai/localai-backends:latest-gpu-vulkan-sam3-cpp - name: vulkan-sam3-cpp-development alias: sam3-cpp license: mit description: | Segment Anything Model (SAM 3/2/EdgeTAM) in C/C++ using GGML. Supports text-prompted and point/box-prompted image segmentation. urls: - https://github.com/PABannier/sam3.cpp tags: - image-segmentation - object-detection - sam3 - gpu - cpu capabilities: default: cpu-sam3-cpp intel: intel-sycl-f32-sam3-cpp metal: metal-sam3-cpp nvidia: cuda12-sam3-cpp nvidia-cuda-12: cuda12-sam3-cpp nvidia-cuda-13: cuda13-sam3-cpp nvidia-l4t: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-sam3-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-sam3-cpp vulkan: vulkan-sam3-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-sam3-cpp mirrors: - localai/localai-backends:master-gpu-vulkan-sam3-cpp - name: rfdetr-cpp-development alias: rfdetr-cpp license: apache-2.0 description: | Native RF-DETR object detection and instance segmentation in C/C++ using GGML. Loads pre-built GGUF weights from the mudler/rfdetr-cpp-* family (Nano/Small/Base/Medium/Large + SegNano/SegSmall/SegMedium) and returns bounding boxes, class labels, confidence scores, and (for segmentation variants) PNG-encoded per-detection masks. urls: - https://github.com/localai-org/rf-detr.cpp tags: - object-detection - image-segmentation - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr-cpp-development intel: intel-sycl-f32-rfdetr-cpp-development metal: metal-rfdetr-cpp-development nvidia: cuda12-rfdetr-cpp-development nvidia-cuda-12: cuda12-rfdetr-cpp-development nvidia-cuda-13: cuda13-rfdetr-cpp-development nvidia-l4t: nvidia-l4t-arm64-rfdetr-cpp-development nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr-cpp-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-rfdetr-cpp-development vulkan: vulkan-rfdetr-cpp-development - name: cpu-rfdetr-cpp alias: rfdetr-cpp license: apache-2.0 description: | Native RF-DETR object detection and instance segmentation in C/C++ using GGML. Loads pre-built GGUF weights from the mudler/rfdetr-cpp-* family (Nano/Small/Base/Medium/Large + SegNano/SegSmall/SegMedium) and returns bounding boxes, class labels, confidence scores, and (for segmentation variants) PNG-encoded per-detection masks. urls: - https://github.com/localai-org/rf-detr.cpp tags: - object-detection - image-segmentation - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr-cpp intel: intel-sycl-f32-rfdetr-cpp metal: metal-rfdetr-cpp nvidia: cuda12-rfdetr-cpp nvidia-cuda-12: cuda12-rfdetr-cpp nvidia-cuda-13: cuda13-rfdetr-cpp nvidia-l4t: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-rfdetr-cpp vulkan: vulkan-rfdetr-cpp uri: quay.io/go-skynet/local-ai-backends:latest-cpu-rfdetr-cpp mirrors: - localai/localai-backends:latest-cpu-rfdetr-cpp - name: cpu-rfdetr-cpp-development alias: rfdetr-cpp license: apache-2.0 description: | Native RF-DETR object detection and instance segmentation in C/C++ using GGML. Loads pre-built GGUF weights from the mudler/rfdetr-cpp-* family (Nano/Small/Base/Medium/Large + SegNano/SegSmall/SegMedium) and returns bounding boxes, class labels, confidence scores, and (for segmentation variants) PNG-encoded per-detection masks. urls: - https://github.com/localai-org/rf-detr.cpp tags: - object-detection - image-segmentation - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr-cpp intel: intel-sycl-f32-rfdetr-cpp metal: metal-rfdetr-cpp nvidia: cuda12-rfdetr-cpp nvidia-cuda-12: cuda12-rfdetr-cpp nvidia-cuda-13: cuda13-rfdetr-cpp nvidia-l4t: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-rfdetr-cpp vulkan: vulkan-rfdetr-cpp uri: quay.io/go-skynet/local-ai-backends:master-cpu-rfdetr-cpp mirrors: - localai/localai-backends:master-cpu-rfdetr-cpp - name: metal-rfdetr-cpp alias: rfdetr-cpp license: apache-2.0 description: | Native RF-DETR object detection and instance segmentation in C/C++ using GGML. Loads pre-built GGUF weights from the mudler/rfdetr-cpp-* family (Nano/Small/Base/Medium/Large + SegNano/SegSmall/SegMedium) and returns bounding boxes, class labels, confidence scores, and (for segmentation variants) PNG-encoded per-detection masks. urls: - https://github.com/localai-org/rf-detr.cpp tags: - object-detection - image-segmentation - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr-cpp intel: intel-sycl-f32-rfdetr-cpp metal: metal-rfdetr-cpp nvidia: cuda12-rfdetr-cpp nvidia-cuda-12: cuda12-rfdetr-cpp nvidia-cuda-13: cuda13-rfdetr-cpp nvidia-l4t: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-rfdetr-cpp vulkan: vulkan-rfdetr-cpp uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-rfdetr-cpp mirrors: - localai/localai-backends:latest-metal-darwin-arm64-rfdetr-cpp - name: metal-rfdetr-cpp-development alias: rfdetr-cpp license: apache-2.0 description: | Native RF-DETR object detection and instance segmentation in C/C++ using GGML. Loads pre-built GGUF weights from the mudler/rfdetr-cpp-* family (Nano/Small/Base/Medium/Large + SegNano/SegSmall/SegMedium) and returns bounding boxes, class labels, confidence scores, and (for segmentation variants) PNG-encoded per-detection masks. urls: - https://github.com/localai-org/rf-detr.cpp tags: - object-detection - image-segmentation - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr-cpp intel: intel-sycl-f32-rfdetr-cpp metal: metal-rfdetr-cpp nvidia: cuda12-rfdetr-cpp nvidia-cuda-12: cuda12-rfdetr-cpp nvidia-cuda-13: cuda13-rfdetr-cpp nvidia-l4t: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-rfdetr-cpp vulkan: vulkan-rfdetr-cpp uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-rfdetr-cpp mirrors: - localai/localai-backends:master-metal-darwin-arm64-rfdetr-cpp - name: cuda12-rfdetr-cpp alias: rfdetr-cpp license: apache-2.0 description: | Native RF-DETR object detection and instance segmentation in C/C++ using GGML. Loads pre-built GGUF weights from the mudler/rfdetr-cpp-* family (Nano/Small/Base/Medium/Large + SegNano/SegSmall/SegMedium) and returns bounding boxes, class labels, confidence scores, and (for segmentation variants) PNG-encoded per-detection masks. urls: - https://github.com/localai-org/rf-detr.cpp tags: - object-detection - image-segmentation - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr-cpp intel: intel-sycl-f32-rfdetr-cpp metal: metal-rfdetr-cpp nvidia: cuda12-rfdetr-cpp nvidia-cuda-12: cuda12-rfdetr-cpp nvidia-cuda-13: cuda13-rfdetr-cpp nvidia-l4t: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-rfdetr-cpp vulkan: vulkan-rfdetr-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-rfdetr-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-rfdetr-cpp - name: cuda12-rfdetr-cpp-development alias: rfdetr-cpp license: apache-2.0 description: | Native RF-DETR object detection and instance segmentation in C/C++ using GGML. Loads pre-built GGUF weights from the mudler/rfdetr-cpp-* family (Nano/Small/Base/Medium/Large + SegNano/SegSmall/SegMedium) and returns bounding boxes, class labels, confidence scores, and (for segmentation variants) PNG-encoded per-detection masks. urls: - https://github.com/localai-org/rf-detr.cpp tags: - object-detection - image-segmentation - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr-cpp intel: intel-sycl-f32-rfdetr-cpp metal: metal-rfdetr-cpp nvidia: cuda12-rfdetr-cpp nvidia-cuda-12: cuda12-rfdetr-cpp nvidia-cuda-13: cuda13-rfdetr-cpp nvidia-l4t: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-rfdetr-cpp vulkan: vulkan-rfdetr-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-rfdetr-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-rfdetr-cpp - name: cuda13-rfdetr-cpp alias: rfdetr-cpp license: apache-2.0 description: | Native RF-DETR object detection and instance segmentation in C/C++ using GGML. Loads pre-built GGUF weights from the mudler/rfdetr-cpp-* family (Nano/Small/Base/Medium/Large + SegNano/SegSmall/SegMedium) and returns bounding boxes, class labels, confidence scores, and (for segmentation variants) PNG-encoded per-detection masks. urls: - https://github.com/localai-org/rf-detr.cpp tags: - object-detection - image-segmentation - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr-cpp intel: intel-sycl-f32-rfdetr-cpp metal: metal-rfdetr-cpp nvidia: cuda12-rfdetr-cpp nvidia-cuda-12: cuda12-rfdetr-cpp nvidia-cuda-13: cuda13-rfdetr-cpp nvidia-l4t: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-rfdetr-cpp vulkan: vulkan-rfdetr-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-rfdetr-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-rfdetr-cpp - name: cuda13-rfdetr-cpp-development alias: rfdetr-cpp license: apache-2.0 description: | Native RF-DETR object detection and instance segmentation in C/C++ using GGML. Loads pre-built GGUF weights from the mudler/rfdetr-cpp-* family (Nano/Small/Base/Medium/Large + SegNano/SegSmall/SegMedium) and returns bounding boxes, class labels, confidence scores, and (for segmentation variants) PNG-encoded per-detection masks. urls: - https://github.com/localai-org/rf-detr.cpp tags: - object-detection - image-segmentation - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr-cpp intel: intel-sycl-f32-rfdetr-cpp metal: metal-rfdetr-cpp nvidia: cuda12-rfdetr-cpp nvidia-cuda-12: cuda12-rfdetr-cpp nvidia-cuda-13: cuda13-rfdetr-cpp nvidia-l4t: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-rfdetr-cpp vulkan: vulkan-rfdetr-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-rfdetr-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-rfdetr-cpp - name: nvidia-l4t-arm64-rfdetr-cpp alias: rfdetr-cpp license: apache-2.0 description: | Native RF-DETR object detection and instance segmentation in C/C++ using GGML. Loads pre-built GGUF weights from the mudler/rfdetr-cpp-* family (Nano/Small/Base/Medium/Large + SegNano/SegSmall/SegMedium) and returns bounding boxes, class labels, confidence scores, and (for segmentation variants) PNG-encoded per-detection masks. urls: - https://github.com/localai-org/rf-detr.cpp tags: - object-detection - image-segmentation - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr-cpp intel: intel-sycl-f32-rfdetr-cpp metal: metal-rfdetr-cpp nvidia: cuda12-rfdetr-cpp nvidia-cuda-12: cuda12-rfdetr-cpp nvidia-cuda-13: cuda13-rfdetr-cpp nvidia-l4t: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-rfdetr-cpp vulkan: vulkan-rfdetr-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-rfdetr-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-arm64-rfdetr-cpp - name: nvidia-l4t-arm64-rfdetr-cpp-development alias: rfdetr-cpp license: apache-2.0 description: | Native RF-DETR object detection and instance segmentation in C/C++ using GGML. Loads pre-built GGUF weights from the mudler/rfdetr-cpp-* family (Nano/Small/Base/Medium/Large + SegNano/SegSmall/SegMedium) and returns bounding boxes, class labels, confidence scores, and (for segmentation variants) PNG-encoded per-detection masks. urls: - https://github.com/localai-org/rf-detr.cpp tags: - object-detection - image-segmentation - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr-cpp intel: intel-sycl-f32-rfdetr-cpp metal: metal-rfdetr-cpp nvidia: cuda12-rfdetr-cpp nvidia-cuda-12: cuda12-rfdetr-cpp nvidia-cuda-13: cuda13-rfdetr-cpp nvidia-l4t: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-rfdetr-cpp vulkan: vulkan-rfdetr-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-rfdetr-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-arm64-rfdetr-cpp - name: cuda13-nvidia-l4t-arm64-rfdetr-cpp alias: rfdetr-cpp license: apache-2.0 description: | Native RF-DETR object detection and instance segmentation in C/C++ using GGML. Loads pre-built GGUF weights from the mudler/rfdetr-cpp-* family (Nano/Small/Base/Medium/Large + SegNano/SegSmall/SegMedium) and returns bounding boxes, class labels, confidence scores, and (for segmentation variants) PNG-encoded per-detection masks. urls: - https://github.com/localai-org/rf-detr.cpp tags: - object-detection - image-segmentation - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr-cpp intel: intel-sycl-f32-rfdetr-cpp metal: metal-rfdetr-cpp nvidia: cuda12-rfdetr-cpp nvidia-cuda-12: cuda12-rfdetr-cpp nvidia-cuda-13: cuda13-rfdetr-cpp nvidia-l4t: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-rfdetr-cpp vulkan: vulkan-rfdetr-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-rfdetr-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-rfdetr-cpp - name: cuda13-nvidia-l4t-arm64-rfdetr-cpp-development alias: rfdetr-cpp license: apache-2.0 description: | Native RF-DETR object detection and instance segmentation in C/C++ using GGML. Loads pre-built GGUF weights from the mudler/rfdetr-cpp-* family (Nano/Small/Base/Medium/Large + SegNano/SegSmall/SegMedium) and returns bounding boxes, class labels, confidence scores, and (for segmentation variants) PNG-encoded per-detection masks. urls: - https://github.com/localai-org/rf-detr.cpp tags: - object-detection - image-segmentation - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr-cpp intel: intel-sycl-f32-rfdetr-cpp metal: metal-rfdetr-cpp nvidia: cuda12-rfdetr-cpp nvidia-cuda-12: cuda12-rfdetr-cpp nvidia-cuda-13: cuda13-rfdetr-cpp nvidia-l4t: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-rfdetr-cpp vulkan: vulkan-rfdetr-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-rfdetr-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-rfdetr-cpp - name: intel-sycl-f32-rfdetr-cpp alias: rfdetr-cpp license: apache-2.0 description: | Native RF-DETR object detection and instance segmentation in C/C++ using GGML. Loads pre-built GGUF weights from the mudler/rfdetr-cpp-* family (Nano/Small/Base/Medium/Large + SegNano/SegSmall/SegMedium) and returns bounding boxes, class labels, confidence scores, and (for segmentation variants) PNG-encoded per-detection masks. urls: - https://github.com/localai-org/rf-detr.cpp tags: - object-detection - image-segmentation - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr-cpp intel: intel-sycl-f32-rfdetr-cpp metal: metal-rfdetr-cpp nvidia: cuda12-rfdetr-cpp nvidia-cuda-12: cuda12-rfdetr-cpp nvidia-cuda-13: cuda13-rfdetr-cpp nvidia-l4t: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-rfdetr-cpp vulkan: vulkan-rfdetr-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-rfdetr-cpp mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f32-rfdetr-cpp - name: intel-sycl-f32-rfdetr-cpp-development alias: rfdetr-cpp license: apache-2.0 description: | Native RF-DETR object detection and instance segmentation in C/C++ using GGML. Loads pre-built GGUF weights from the mudler/rfdetr-cpp-* family (Nano/Small/Base/Medium/Large + SegNano/SegSmall/SegMedium) and returns bounding boxes, class labels, confidence scores, and (for segmentation variants) PNG-encoded per-detection masks. urls: - https://github.com/localai-org/rf-detr.cpp tags: - object-detection - image-segmentation - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr-cpp intel: intel-sycl-f32-rfdetr-cpp metal: metal-rfdetr-cpp nvidia: cuda12-rfdetr-cpp nvidia-cuda-12: cuda12-rfdetr-cpp nvidia-cuda-13: cuda13-rfdetr-cpp nvidia-l4t: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-rfdetr-cpp vulkan: vulkan-rfdetr-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-rfdetr-cpp mirrors: - localai/localai-backends:master-gpu-intel-sycl-f32-rfdetr-cpp - name: intel-sycl-f16-rfdetr-cpp alias: rfdetr-cpp license: apache-2.0 description: | Native RF-DETR object detection and instance segmentation in C/C++ using GGML. Loads pre-built GGUF weights from the mudler/rfdetr-cpp-* family (Nano/Small/Base/Medium/Large + SegNano/SegSmall/SegMedium) and returns bounding boxes, class labels, confidence scores, and (for segmentation variants) PNG-encoded per-detection masks. urls: - https://github.com/localai-org/rf-detr.cpp tags: - object-detection - image-segmentation - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr-cpp intel: intel-sycl-f32-rfdetr-cpp metal: metal-rfdetr-cpp nvidia: cuda12-rfdetr-cpp nvidia-cuda-12: cuda12-rfdetr-cpp nvidia-cuda-13: cuda13-rfdetr-cpp nvidia-l4t: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-rfdetr-cpp vulkan: vulkan-rfdetr-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-rfdetr-cpp mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f16-rfdetr-cpp - name: intel-sycl-f16-rfdetr-cpp-development alias: rfdetr-cpp license: apache-2.0 description: | Native RF-DETR object detection and instance segmentation in C/C++ using GGML. Loads pre-built GGUF weights from the mudler/rfdetr-cpp-* family (Nano/Small/Base/Medium/Large + SegNano/SegSmall/SegMedium) and returns bounding boxes, class labels, confidence scores, and (for segmentation variants) PNG-encoded per-detection masks. urls: - https://github.com/localai-org/rf-detr.cpp tags: - object-detection - image-segmentation - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr-cpp intel: intel-sycl-f32-rfdetr-cpp metal: metal-rfdetr-cpp nvidia: cuda12-rfdetr-cpp nvidia-cuda-12: cuda12-rfdetr-cpp nvidia-cuda-13: cuda13-rfdetr-cpp nvidia-l4t: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-rfdetr-cpp vulkan: vulkan-rfdetr-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-rfdetr-cpp mirrors: - localai/localai-backends:master-gpu-intel-sycl-f16-rfdetr-cpp - name: vulkan-rfdetr-cpp alias: rfdetr-cpp license: apache-2.0 description: | Native RF-DETR object detection and instance segmentation in C/C++ using GGML. Loads pre-built GGUF weights from the mudler/rfdetr-cpp-* family (Nano/Small/Base/Medium/Large + SegNano/SegSmall/SegMedium) and returns bounding boxes, class labels, confidence scores, and (for segmentation variants) PNG-encoded per-detection masks. urls: - https://github.com/localai-org/rf-detr.cpp tags: - object-detection - image-segmentation - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr-cpp intel: intel-sycl-f32-rfdetr-cpp metal: metal-rfdetr-cpp nvidia: cuda12-rfdetr-cpp nvidia-cuda-12: cuda12-rfdetr-cpp nvidia-cuda-13: cuda13-rfdetr-cpp nvidia-l4t: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-rfdetr-cpp vulkan: vulkan-rfdetr-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-rfdetr-cpp mirrors: - localai/localai-backends:latest-gpu-vulkan-rfdetr-cpp - name: vulkan-rfdetr-cpp-development alias: rfdetr-cpp license: apache-2.0 description: | Native RF-DETR object detection and instance segmentation in C/C++ using GGML. Loads pre-built GGUF weights from the mudler/rfdetr-cpp-* family (Nano/Small/Base/Medium/Large + SegNano/SegSmall/SegMedium) and returns bounding boxes, class labels, confidence scores, and (for segmentation variants) PNG-encoded per-detection masks. urls: - https://github.com/localai-org/rf-detr.cpp tags: - object-detection - image-segmentation - rfdetr - gpu - cpu capabilities: default: cpu-rfdetr-cpp intel: intel-sycl-f32-rfdetr-cpp metal: metal-rfdetr-cpp nvidia: cuda12-rfdetr-cpp nvidia-cuda-12: cuda12-rfdetr-cpp nvidia-cuda-13: cuda13-rfdetr-cpp nvidia-l4t: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-rfdetr-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-rfdetr-cpp vulkan: vulkan-rfdetr-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-rfdetr-cpp mirrors: - localai/localai-backends:master-gpu-vulkan-rfdetr-cpp - name: rerankers-development alias: rerankers capabilities: amd: rocm-rerankers-development intel: intel-rerankers-development metal: metal-rerankers-development nvidia: cuda12-rerankers-development nvidia-cuda-13: cuda13-rerankers-development - name: cuda12-rerankers alias: rerankers capabilities: amd: rocm-rerankers intel: intel-rerankers metal: metal-rerankers nvidia: cuda12-rerankers uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-rerankers mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-rerankers - name: intel-rerankers alias: rerankers capabilities: amd: rocm-rerankers intel: intel-rerankers metal: metal-rerankers nvidia: cuda12-rerankers uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-rerankers mirrors: - localai/localai-backends:latest-gpu-intel-rerankers - name: rocm-rerankers alias: rerankers capabilities: amd: rocm-rerankers intel: intel-rerankers metal: metal-rerankers nvidia: cuda12-rerankers uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-rerankers mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-rerankers - name: cuda12-rerankers-development alias: rerankers capabilities: amd: rocm-rerankers intel: intel-rerankers metal: metal-rerankers nvidia: cuda12-rerankers uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-rerankers mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-rerankers - name: rocm-rerankers-development alias: rerankers capabilities: amd: rocm-rerankers intel: intel-rerankers metal: metal-rerankers nvidia: cuda12-rerankers uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-rerankers mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-rerankers - name: intel-rerankers-development alias: rerankers capabilities: amd: rocm-rerankers intel: intel-rerankers metal: metal-rerankers nvidia: cuda12-rerankers uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-rerankers mirrors: - localai/localai-backends:master-gpu-intel-rerankers - name: cuda13-rerankers alias: rerankers capabilities: amd: rocm-rerankers intel: intel-rerankers metal: metal-rerankers nvidia: cuda12-rerankers uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-rerankers mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-rerankers - name: cuda13-rerankers-development alias: rerankers capabilities: amd: rocm-rerankers intel: intel-rerankers metal: metal-rerankers nvidia: cuda12-rerankers uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-rerankers mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-rerankers - name: metal-rerankers alias: rerankers capabilities: amd: rocm-rerankers intel: intel-rerankers metal: metal-rerankers nvidia: cuda12-rerankers uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-rerankers mirrors: - localai/localai-backends:latest-metal-darwin-arm64-rerankers - name: metal-rerankers-development alias: rerankers capabilities: amd: rocm-rerankers intel: intel-rerankers metal: metal-rerankers nvidia: cuda12-rerankers uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-rerankers mirrors: - localai/localai-backends:master-metal-darwin-arm64-rerankers - name: tinygrad-development alias: tinygrad license: MIT description: | tinygrad is a minimalist deep-learning framework with zero runtime dependencies that targets CUDA, ROCm, Metal, WebGPU and CPU (CLANG). The LocalAI tinygrad backend exposes a single multimodal runtime that covers LLM text generation (Llama / Qwen / Mistral via safetensors or GGUF) with native tool-call extraction, BERT-family embeddings, Stable Diffusion 1.x / 2 / XL image generation, and Whisper speech-to-text. Single image: tinygrad generates its own GPU kernels and dlopens the host driver libraries at runtime, so there is no per-toolkit build split. The same image runs CPU-only or accelerates against CUDA / ROCm / Metal when the host driver is visible. urls: - https://github.com/tinygrad/tinygrad tags: - text-to-text - LLM - embeddings - image-generation - transcription - multimodal uri: quay.io/go-skynet/local-ai-backends:master-tinygrad mirrors: - localai/localai-backends:master-tinygrad - name: transformers-development alias: transformers license: apache-2.0 icon: https://avatars.githubusercontent.com/u/25720743?s=200&v=4 description: | Transformers acts as the model-definition framework for state-of-the-art machine learning models in text, computer vision, audio, video, and multimodal model, for both inference and training. It centralizes the model definition so that this definition is agreed upon across the ecosystem. transformers is the pivot across frameworks: if a model definition is supported, it will be compatible with the majority of training frameworks (Axolotl, Unsloth, DeepSpeed, FSDP, PyTorch-Lightning, ...), inference engines (vLLM, SGLang, TGI, ...), and adjacent modeling libraries (llama.cpp, mlx, ...) which leverage the model definition from transformers. urls: - https://github.com/huggingface/transformers tags: - text-to-text - multimodal capabilities: amd: rocm-transformers-development intel: intel-transformers-development metal: metal-transformers-development nvidia: cuda12-transformers-development nvidia-cuda-13: cuda13-transformers-development - name: cuda12-transformers alias: transformers license: apache-2.0 icon: https://avatars.githubusercontent.com/u/25720743?s=200&v=4 description: | Transformers acts as the model-definition framework for state-of-the-art machine learning models in text, computer vision, audio, video, and multimodal model, for both inference and training. It centralizes the model definition so that this definition is agreed upon across the ecosystem. transformers is the pivot across frameworks: if a model definition is supported, it will be compatible with the majority of training frameworks (Axolotl, Unsloth, DeepSpeed, FSDP, PyTorch-Lightning, ...), inference engines (vLLM, SGLang, TGI, ...), and adjacent modeling libraries (llama.cpp, mlx, ...) which leverage the model definition from transformers. urls: - https://github.com/huggingface/transformers tags: - text-to-text - multimodal capabilities: amd: rocm-transformers intel: intel-transformers metal: metal-transformers nvidia: cuda12-transformers nvidia-cuda-12: cuda12-transformers nvidia-cuda-13: cuda13-transformers uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-transformers mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-transformers - name: rocm-transformers alias: transformers license: apache-2.0 icon: https://avatars.githubusercontent.com/u/25720743?s=200&v=4 description: | Transformers acts as the model-definition framework for state-of-the-art machine learning models in text, computer vision, audio, video, and multimodal model, for both inference and training. It centralizes the model definition so that this definition is agreed upon across the ecosystem. transformers is the pivot across frameworks: if a model definition is supported, it will be compatible with the majority of training frameworks (Axolotl, Unsloth, DeepSpeed, FSDP, PyTorch-Lightning, ...), inference engines (vLLM, SGLang, TGI, ...), and adjacent modeling libraries (llama.cpp, mlx, ...) which leverage the model definition from transformers. urls: - https://github.com/huggingface/transformers tags: - text-to-text - multimodal capabilities: amd: rocm-transformers intel: intel-transformers metal: metal-transformers nvidia: cuda12-transformers nvidia-cuda-12: cuda12-transformers nvidia-cuda-13: cuda13-transformers uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-transformers mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-transformers - name: intel-transformers alias: transformers license: apache-2.0 icon: https://avatars.githubusercontent.com/u/25720743?s=200&v=4 description: | Transformers acts as the model-definition framework for state-of-the-art machine learning models in text, computer vision, audio, video, and multimodal model, for both inference and training. It centralizes the model definition so that this definition is agreed upon across the ecosystem. transformers is the pivot across frameworks: if a model definition is supported, it will be compatible with the majority of training frameworks (Axolotl, Unsloth, DeepSpeed, FSDP, PyTorch-Lightning, ...), inference engines (vLLM, SGLang, TGI, ...), and adjacent modeling libraries (llama.cpp, mlx, ...) which leverage the model definition from transformers. urls: - https://github.com/huggingface/transformers tags: - text-to-text - multimodal capabilities: amd: rocm-transformers intel: intel-transformers metal: metal-transformers nvidia: cuda12-transformers nvidia-cuda-12: cuda12-transformers nvidia-cuda-13: cuda13-transformers uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-transformers mirrors: - localai/localai-backends:latest-gpu-intel-transformers - name: cuda12-transformers-development alias: transformers license: apache-2.0 icon: https://avatars.githubusercontent.com/u/25720743?s=200&v=4 description: | Transformers acts as the model-definition framework for state-of-the-art machine learning models in text, computer vision, audio, video, and multimodal model, for both inference and training. It centralizes the model definition so that this definition is agreed upon across the ecosystem. transformers is the pivot across frameworks: if a model definition is supported, it will be compatible with the majority of training frameworks (Axolotl, Unsloth, DeepSpeed, FSDP, PyTorch-Lightning, ...), inference engines (vLLM, SGLang, TGI, ...), and adjacent modeling libraries (llama.cpp, mlx, ...) which leverage the model definition from transformers. urls: - https://github.com/huggingface/transformers tags: - text-to-text - multimodal capabilities: amd: rocm-transformers intel: intel-transformers metal: metal-transformers nvidia: cuda12-transformers nvidia-cuda-12: cuda12-transformers nvidia-cuda-13: cuda13-transformers uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-transformers mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-transformers - name: rocm-transformers-development alias: transformers license: apache-2.0 icon: https://avatars.githubusercontent.com/u/25720743?s=200&v=4 description: | Transformers acts as the model-definition framework for state-of-the-art machine learning models in text, computer vision, audio, video, and multimodal model, for both inference and training. It centralizes the model definition so that this definition is agreed upon across the ecosystem. transformers is the pivot across frameworks: if a model definition is supported, it will be compatible with the majority of training frameworks (Axolotl, Unsloth, DeepSpeed, FSDP, PyTorch-Lightning, ...), inference engines (vLLM, SGLang, TGI, ...), and adjacent modeling libraries (llama.cpp, mlx, ...) which leverage the model definition from transformers. urls: - https://github.com/huggingface/transformers tags: - text-to-text - multimodal capabilities: amd: rocm-transformers intel: intel-transformers metal: metal-transformers nvidia: cuda12-transformers nvidia-cuda-12: cuda12-transformers nvidia-cuda-13: cuda13-transformers uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-transformers mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-transformers - name: intel-transformers-development alias: transformers license: apache-2.0 icon: https://avatars.githubusercontent.com/u/25720743?s=200&v=4 description: | Transformers acts as the model-definition framework for state-of-the-art machine learning models in text, computer vision, audio, video, and multimodal model, for both inference and training. It centralizes the model definition so that this definition is agreed upon across the ecosystem. transformers is the pivot across frameworks: if a model definition is supported, it will be compatible with the majority of training frameworks (Axolotl, Unsloth, DeepSpeed, FSDP, PyTorch-Lightning, ...), inference engines (vLLM, SGLang, TGI, ...), and adjacent modeling libraries (llama.cpp, mlx, ...) which leverage the model definition from transformers. urls: - https://github.com/huggingface/transformers tags: - text-to-text - multimodal capabilities: amd: rocm-transformers intel: intel-transformers metal: metal-transformers nvidia: cuda12-transformers nvidia-cuda-12: cuda12-transformers nvidia-cuda-13: cuda13-transformers uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-transformers mirrors: - localai/localai-backends:master-gpu-intel-transformers - name: cuda13-transformers alias: transformers license: apache-2.0 icon: https://avatars.githubusercontent.com/u/25720743?s=200&v=4 description: | Transformers acts as the model-definition framework for state-of-the-art machine learning models in text, computer vision, audio, video, and multimodal model, for both inference and training. It centralizes the model definition so that this definition is agreed upon across the ecosystem. transformers is the pivot across frameworks: if a model definition is supported, it will be compatible with the majority of training frameworks (Axolotl, Unsloth, DeepSpeed, FSDP, PyTorch-Lightning, ...), inference engines (vLLM, SGLang, TGI, ...), and adjacent modeling libraries (llama.cpp, mlx, ...) which leverage the model definition from transformers. urls: - https://github.com/huggingface/transformers tags: - text-to-text - multimodal capabilities: amd: rocm-transformers intel: intel-transformers metal: metal-transformers nvidia: cuda12-transformers nvidia-cuda-12: cuda12-transformers nvidia-cuda-13: cuda13-transformers uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-transformers mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-transformers - name: cuda13-transformers-development alias: transformers license: apache-2.0 icon: https://avatars.githubusercontent.com/u/25720743?s=200&v=4 description: | Transformers acts as the model-definition framework for state-of-the-art machine learning models in text, computer vision, audio, video, and multimodal model, for both inference and training. It centralizes the model definition so that this definition is agreed upon across the ecosystem. transformers is the pivot across frameworks: if a model definition is supported, it will be compatible with the majority of training frameworks (Axolotl, Unsloth, DeepSpeed, FSDP, PyTorch-Lightning, ...), inference engines (vLLM, SGLang, TGI, ...), and adjacent modeling libraries (llama.cpp, mlx, ...) which leverage the model definition from transformers. urls: - https://github.com/huggingface/transformers tags: - text-to-text - multimodal capabilities: amd: rocm-transformers intel: intel-transformers metal: metal-transformers nvidia: cuda12-transformers nvidia-cuda-12: cuda12-transformers nvidia-cuda-13: cuda13-transformers uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-transformers mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-transformers - name: metal-transformers alias: transformers license: apache-2.0 icon: https://avatars.githubusercontent.com/u/25720743?s=200&v=4 description: | Transformers acts as the model-definition framework for state-of-the-art machine learning models in text, computer vision, audio, video, and multimodal model, for both inference and training. It centralizes the model definition so that this definition is agreed upon across the ecosystem. transformers is the pivot across frameworks: if a model definition is supported, it will be compatible with the majority of training frameworks (Axolotl, Unsloth, DeepSpeed, FSDP, PyTorch-Lightning, ...), inference engines (vLLM, SGLang, TGI, ...), and adjacent modeling libraries (llama.cpp, mlx, ...) which leverage the model definition from transformers. urls: - https://github.com/huggingface/transformers tags: - text-to-text - multimodal capabilities: amd: rocm-transformers intel: intel-transformers metal: metal-transformers nvidia: cuda12-transformers nvidia-cuda-12: cuda12-transformers nvidia-cuda-13: cuda13-transformers uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-transformers mirrors: - localai/localai-backends:latest-metal-darwin-arm64-transformers - name: metal-transformers-development alias: transformers license: apache-2.0 icon: https://avatars.githubusercontent.com/u/25720743?s=200&v=4 description: | Transformers acts as the model-definition framework for state-of-the-art machine learning models in text, computer vision, audio, video, and multimodal model, for both inference and training. It centralizes the model definition so that this definition is agreed upon across the ecosystem. transformers is the pivot across frameworks: if a model definition is supported, it will be compatible with the majority of training frameworks (Axolotl, Unsloth, DeepSpeed, FSDP, PyTorch-Lightning, ...), inference engines (vLLM, SGLang, TGI, ...), and adjacent modeling libraries (llama.cpp, mlx, ...) which leverage the model definition from transformers. urls: - https://github.com/huggingface/transformers tags: - text-to-text - multimodal capabilities: amd: rocm-transformers intel: intel-transformers metal: metal-transformers nvidia: cuda12-transformers nvidia-cuda-12: cuda12-transformers nvidia-cuda-13: cuda13-transformers uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-transformers mirrors: - localai/localai-backends:master-metal-darwin-arm64-transformers - name: diffusers-development alias: diffusers license: apache-2.0 icon: https://raw.githubusercontent.com/huggingface/diffusers/main/docs/source/en/imgs/diffusers_library.jpg description: "\U0001F917 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules. Whether you're looking for a simple inference solution or training your own diffusion models, \U0001F917 Diffusers is a modular toolbox that supports both.\n" urls: - https://github.com/huggingface/diffusers tags: - image-generation - video-generation - sound-generation - diffusion-models capabilities: amd: rocm-diffusers-development default: cpu-diffusers-development intel: intel-diffusers-development metal: metal-diffusers-development nvidia: cuda12-diffusers-development nvidia-cuda-13: cuda13-diffusers-development nvidia-l4t: nvidia-l4t-diffusers-development - name: cpu-diffusers alias: diffusers license: apache-2.0 icon: https://raw.githubusercontent.com/huggingface/diffusers/main/docs/source/en/imgs/diffusers_library.jpg description: "\U0001F917 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules. Whether you're looking for a simple inference solution or training your own diffusion models, \U0001F917 Diffusers is a modular toolbox that supports both.\n" urls: - https://github.com/huggingface/diffusers tags: - image-generation - video-generation - sound-generation - diffusion-models capabilities: amd: rocm-diffusers default: cpu-diffusers intel: intel-diffusers metal: metal-diffusers nvidia: cuda12-diffusers nvidia-cuda-12: cuda12-diffusers nvidia-cuda-13: cuda13-diffusers nvidia-l4t: nvidia-l4t-diffusers nvidia-l4t-cuda-12: nvidia-l4t-diffusers nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-diffusers uri: quay.io/go-skynet/local-ai-backends:latest-cpu-diffusers mirrors: - localai/localai-backends:latest-cpu-diffusers - name: cpu-diffusers-development alias: diffusers license: apache-2.0 icon: https://raw.githubusercontent.com/huggingface/diffusers/main/docs/source/en/imgs/diffusers_library.jpg description: "\U0001F917 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules. Whether you're looking for a simple inference solution or training your own diffusion models, \U0001F917 Diffusers is a modular toolbox that supports both.\n" urls: - https://github.com/huggingface/diffusers tags: - image-generation - video-generation - sound-generation - diffusion-models capabilities: amd: rocm-diffusers default: cpu-diffusers intel: intel-diffusers metal: metal-diffusers nvidia: cuda12-diffusers nvidia-cuda-12: cuda12-diffusers nvidia-cuda-13: cuda13-diffusers nvidia-l4t: nvidia-l4t-diffusers nvidia-l4t-cuda-12: nvidia-l4t-diffusers nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-diffusers uri: quay.io/go-skynet/local-ai-backends:master-cpu-diffusers mirrors: - localai/localai-backends:master-cpu-diffusers - name: nvidia-l4t-diffusers alias: diffusers license: apache-2.0 icon: https://raw.githubusercontent.com/huggingface/diffusers/main/docs/source/en/imgs/diffusers_library.jpg description: "\U0001F917 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules. Whether you're looking for a simple inference solution or training your own diffusion models, \U0001F917 Diffusers is a modular toolbox that supports both.\n" urls: - https://github.com/huggingface/diffusers tags: - image-generation - video-generation - sound-generation - diffusion-models capabilities: amd: rocm-diffusers default: cpu-diffusers intel: intel-diffusers metal: metal-diffusers nvidia: cuda12-diffusers nvidia-cuda-12: cuda12-diffusers nvidia-cuda-13: cuda13-diffusers nvidia-l4t: nvidia-l4t-diffusers nvidia-l4t-cuda-12: nvidia-l4t-diffusers nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-diffusers uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-diffusers mirrors: - localai/localai-backends:latest-nvidia-l4t-diffusers - name: nvidia-l4t-diffusers-development alias: diffusers license: apache-2.0 icon: https://raw.githubusercontent.com/huggingface/diffusers/main/docs/source/en/imgs/diffusers_library.jpg description: "\U0001F917 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules. Whether you're looking for a simple inference solution or training your own diffusion models, \U0001F917 Diffusers is a modular toolbox that supports both.\n" urls: - https://github.com/huggingface/diffusers tags: - image-generation - video-generation - sound-generation - diffusion-models capabilities: amd: rocm-diffusers default: cpu-diffusers intel: intel-diffusers metal: metal-diffusers nvidia: cuda12-diffusers nvidia-cuda-12: cuda12-diffusers nvidia-cuda-13: cuda13-diffusers nvidia-l4t: nvidia-l4t-diffusers nvidia-l4t-cuda-12: nvidia-l4t-diffusers nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-diffusers uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-diffusers mirrors: - localai/localai-backends:master-nvidia-l4t-diffusers - name: cuda13-nvidia-l4t-arm64-diffusers alias: diffusers license: apache-2.0 icon: https://raw.githubusercontent.com/huggingface/diffusers/main/docs/source/en/imgs/diffusers_library.jpg description: "\U0001F917 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules. Whether you're looking for a simple inference solution or training your own diffusion models, \U0001F917 Diffusers is a modular toolbox that supports both.\n" urls: - https://github.com/huggingface/diffusers tags: - image-generation - video-generation - sound-generation - diffusion-models capabilities: amd: rocm-diffusers default: cpu-diffusers intel: intel-diffusers metal: metal-diffusers nvidia: cuda12-diffusers nvidia-cuda-12: cuda12-diffusers nvidia-cuda-13: cuda13-diffusers nvidia-l4t: nvidia-l4t-diffusers nvidia-l4t-cuda-12: nvidia-l4t-diffusers nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-diffusers uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-diffusers mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-diffusers - name: cuda13-nvidia-l4t-arm64-diffusers-development alias: diffusers license: apache-2.0 icon: https://raw.githubusercontent.com/huggingface/diffusers/main/docs/source/en/imgs/diffusers_library.jpg description: "\U0001F917 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules. Whether you're looking for a simple inference solution or training your own diffusion models, \U0001F917 Diffusers is a modular toolbox that supports both.\n" urls: - https://github.com/huggingface/diffusers tags: - image-generation - video-generation - sound-generation - diffusion-models capabilities: amd: rocm-diffusers default: cpu-diffusers intel: intel-diffusers metal: metal-diffusers nvidia: cuda12-diffusers nvidia-cuda-12: cuda12-diffusers nvidia-cuda-13: cuda13-diffusers nvidia-l4t: nvidia-l4t-diffusers nvidia-l4t-cuda-12: nvidia-l4t-diffusers nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-diffusers uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-diffusers mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-diffusers - name: cuda12-diffusers alias: diffusers license: apache-2.0 icon: https://raw.githubusercontent.com/huggingface/diffusers/main/docs/source/en/imgs/diffusers_library.jpg description: "\U0001F917 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules. Whether you're looking for a simple inference solution or training your own diffusion models, \U0001F917 Diffusers is a modular toolbox that supports both.\n" urls: - https://github.com/huggingface/diffusers tags: - image-generation - video-generation - sound-generation - diffusion-models capabilities: amd: rocm-diffusers default: cpu-diffusers intel: intel-diffusers metal: metal-diffusers nvidia: cuda12-diffusers nvidia-cuda-12: cuda12-diffusers nvidia-cuda-13: cuda13-diffusers nvidia-l4t: nvidia-l4t-diffusers nvidia-l4t-cuda-12: nvidia-l4t-diffusers nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-diffusers uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-diffusers mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-diffusers - name: rocm-diffusers alias: diffusers license: apache-2.0 icon: https://raw.githubusercontent.com/huggingface/diffusers/main/docs/source/en/imgs/diffusers_library.jpg description: "\U0001F917 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules. Whether you're looking for a simple inference solution or training your own diffusion models, \U0001F917 Diffusers is a modular toolbox that supports both.\n" urls: - https://github.com/huggingface/diffusers tags: - image-generation - video-generation - sound-generation - diffusion-models capabilities: amd: rocm-diffusers default: cpu-diffusers intel: intel-diffusers metal: metal-diffusers nvidia: cuda12-diffusers nvidia-cuda-12: cuda12-diffusers nvidia-cuda-13: cuda13-diffusers nvidia-l4t: nvidia-l4t-diffusers nvidia-l4t-cuda-12: nvidia-l4t-diffusers nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-diffusers uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-diffusers mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-diffusers - name: intel-diffusers alias: diffusers license: apache-2.0 icon: https://raw.githubusercontent.com/huggingface/diffusers/main/docs/source/en/imgs/diffusers_library.jpg description: "\U0001F917 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules. Whether you're looking for a simple inference solution or training your own diffusion models, \U0001F917 Diffusers is a modular toolbox that supports both.\n" urls: - https://github.com/huggingface/diffusers tags: - image-generation - video-generation - sound-generation - diffusion-models capabilities: amd: rocm-diffusers default: cpu-diffusers intel: intel-diffusers metal: metal-diffusers nvidia: cuda12-diffusers nvidia-cuda-12: cuda12-diffusers nvidia-cuda-13: cuda13-diffusers nvidia-l4t: nvidia-l4t-diffusers nvidia-l4t-cuda-12: nvidia-l4t-diffusers nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-diffusers uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-diffusers mirrors: - localai/localai-backends:latest-gpu-intel-diffusers - name: cuda12-diffusers-development alias: diffusers license: apache-2.0 icon: https://raw.githubusercontent.com/huggingface/diffusers/main/docs/source/en/imgs/diffusers_library.jpg description: "\U0001F917 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules. Whether you're looking for a simple inference solution or training your own diffusion models, \U0001F917 Diffusers is a modular toolbox that supports both.\n" urls: - https://github.com/huggingface/diffusers tags: - image-generation - video-generation - sound-generation - diffusion-models capabilities: amd: rocm-diffusers default: cpu-diffusers intel: intel-diffusers metal: metal-diffusers nvidia: cuda12-diffusers nvidia-cuda-12: cuda12-diffusers nvidia-cuda-13: cuda13-diffusers nvidia-l4t: nvidia-l4t-diffusers nvidia-l4t-cuda-12: nvidia-l4t-diffusers nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-diffusers uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-diffusers mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-diffusers - name: rocm-diffusers-development alias: diffusers license: apache-2.0 icon: https://raw.githubusercontent.com/huggingface/diffusers/main/docs/source/en/imgs/diffusers_library.jpg description: "\U0001F917 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules. Whether you're looking for a simple inference solution or training your own diffusion models, \U0001F917 Diffusers is a modular toolbox that supports both.\n" urls: - https://github.com/huggingface/diffusers tags: - image-generation - video-generation - sound-generation - diffusion-models capabilities: amd: rocm-diffusers default: cpu-diffusers intel: intel-diffusers metal: metal-diffusers nvidia: cuda12-diffusers nvidia-cuda-12: cuda12-diffusers nvidia-cuda-13: cuda13-diffusers nvidia-l4t: nvidia-l4t-diffusers nvidia-l4t-cuda-12: nvidia-l4t-diffusers nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-diffusers uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-diffusers mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-diffusers - name: intel-diffusers-development alias: diffusers license: apache-2.0 icon: https://raw.githubusercontent.com/huggingface/diffusers/main/docs/source/en/imgs/diffusers_library.jpg description: "\U0001F917 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules. Whether you're looking for a simple inference solution or training your own diffusion models, \U0001F917 Diffusers is a modular toolbox that supports both.\n" urls: - https://github.com/huggingface/diffusers tags: - image-generation - video-generation - sound-generation - diffusion-models capabilities: amd: rocm-diffusers default: cpu-diffusers intel: intel-diffusers metal: metal-diffusers nvidia: cuda12-diffusers nvidia-cuda-12: cuda12-diffusers nvidia-cuda-13: cuda13-diffusers nvidia-l4t: nvidia-l4t-diffusers nvidia-l4t-cuda-12: nvidia-l4t-diffusers nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-diffusers uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-diffusers mirrors: - localai/localai-backends:master-gpu-intel-diffusers - name: cuda13-diffusers alias: diffusers license: apache-2.0 icon: https://raw.githubusercontent.com/huggingface/diffusers/main/docs/source/en/imgs/diffusers_library.jpg description: "\U0001F917 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules. Whether you're looking for a simple inference solution or training your own diffusion models, \U0001F917 Diffusers is a modular toolbox that supports both.\n" urls: - https://github.com/huggingface/diffusers tags: - image-generation - video-generation - sound-generation - diffusion-models capabilities: amd: rocm-diffusers default: cpu-diffusers intel: intel-diffusers metal: metal-diffusers nvidia: cuda12-diffusers nvidia-cuda-12: cuda12-diffusers nvidia-cuda-13: cuda13-diffusers nvidia-l4t: nvidia-l4t-diffusers nvidia-l4t-cuda-12: nvidia-l4t-diffusers nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-diffusers uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-diffusers mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-diffusers - name: cuda13-diffusers-development alias: diffusers license: apache-2.0 icon: https://raw.githubusercontent.com/huggingface/diffusers/main/docs/source/en/imgs/diffusers_library.jpg description: "\U0001F917 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules. Whether you're looking for a simple inference solution or training your own diffusion models, \U0001F917 Diffusers is a modular toolbox that supports both.\n" urls: - https://github.com/huggingface/diffusers tags: - image-generation - video-generation - sound-generation - diffusion-models capabilities: amd: rocm-diffusers default: cpu-diffusers intel: intel-diffusers metal: metal-diffusers nvidia: cuda12-diffusers nvidia-cuda-12: cuda12-diffusers nvidia-cuda-13: cuda13-diffusers nvidia-l4t: nvidia-l4t-diffusers nvidia-l4t-cuda-12: nvidia-l4t-diffusers nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-diffusers uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-diffusers mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-diffusers - name: metal-diffusers alias: diffusers license: apache-2.0 icon: https://raw.githubusercontent.com/huggingface/diffusers/main/docs/source/en/imgs/diffusers_library.jpg description: "\U0001F917 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules. Whether you're looking for a simple inference solution or training your own diffusion models, \U0001F917 Diffusers is a modular toolbox that supports both.\n" urls: - https://github.com/huggingface/diffusers tags: - image-generation - video-generation - sound-generation - diffusion-models capabilities: amd: rocm-diffusers default: cpu-diffusers intel: intel-diffusers metal: metal-diffusers nvidia: cuda12-diffusers nvidia-cuda-12: cuda12-diffusers nvidia-cuda-13: cuda13-diffusers nvidia-l4t: nvidia-l4t-diffusers nvidia-l4t-cuda-12: nvidia-l4t-diffusers nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-diffusers uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-diffusers mirrors: - localai/localai-backends:latest-metal-darwin-arm64-diffusers - name: metal-diffusers-development alias: diffusers license: apache-2.0 icon: https://raw.githubusercontent.com/huggingface/diffusers/main/docs/source/en/imgs/diffusers_library.jpg description: "\U0001F917 Diffusers is the go-to library for state-of-the-art pretrained diffusion models for generating images, audio, and even 3D structures of molecules. Whether you're looking for a simple inference solution or training your own diffusion models, \U0001F917 Diffusers is a modular toolbox that supports both.\n" urls: - https://github.com/huggingface/diffusers tags: - image-generation - video-generation - sound-generation - diffusion-models capabilities: amd: rocm-diffusers default: cpu-diffusers intel: intel-diffusers metal: metal-diffusers nvidia: cuda12-diffusers nvidia-cuda-12: cuda12-diffusers nvidia-cuda-13: cuda13-diffusers nvidia-l4t: nvidia-l4t-diffusers nvidia-l4t-cuda-12: nvidia-l4t-diffusers nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-diffusers uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-diffusers mirrors: - localai/localai-backends:master-metal-darwin-arm64-diffusers - name: cpu-ace-step alias: ace-step description: | ACE-Step 1.5 is an open-source music generation model. It supports simple mode (natural language description) and advanced mode (caption, lyrics, think, bpm, keyscale, etc.). Uses in-process acestep (LLMHandler for metadata, DiT for audio). urls: - https://github.com/ace-step/ACE-Step-1.5 tags: - music-generation - sound-generation capabilities: amd: rocm-ace-step default: cpu-ace-step intel: intel-ace-step metal: metal-ace-step nvidia: cuda12-ace-step nvidia-cuda-12: cuda12-ace-step nvidia-cuda-13: cuda13-ace-step uri: quay.io/go-skynet/local-ai-backends:latest-cpu-ace-step mirrors: - localai/localai-backends:latest-cpu-ace-step - name: cpu-ace-step-development alias: ace-step description: | ACE-Step 1.5 is an open-source music generation model. It supports simple mode (natural language description) and advanced mode (caption, lyrics, think, bpm, keyscale, etc.). Uses in-process acestep (LLMHandler for metadata, DiT for audio). urls: - https://github.com/ace-step/ACE-Step-1.5 tags: - music-generation - sound-generation capabilities: amd: rocm-ace-step default: cpu-ace-step intel: intel-ace-step metal: metal-ace-step nvidia: cuda12-ace-step nvidia-cuda-12: cuda12-ace-step nvidia-cuda-13: cuda13-ace-step uri: quay.io/go-skynet/local-ai-backends:master-cpu-ace-step mirrors: - localai/localai-backends:master-cpu-ace-step - name: cuda12-ace-step alias: ace-step description: | ACE-Step 1.5 is an open-source music generation model. It supports simple mode (natural language description) and advanced mode (caption, lyrics, think, bpm, keyscale, etc.). Uses in-process acestep (LLMHandler for metadata, DiT for audio). urls: - https://github.com/ace-step/ACE-Step-1.5 tags: - music-generation - sound-generation capabilities: amd: rocm-ace-step default: cpu-ace-step intel: intel-ace-step metal: metal-ace-step nvidia: cuda12-ace-step nvidia-cuda-12: cuda12-ace-step nvidia-cuda-13: cuda13-ace-step uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-ace-step mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-ace-step - name: cuda12-ace-step-development alias: ace-step description: | ACE-Step 1.5 is an open-source music generation model. It supports simple mode (natural language description) and advanced mode (caption, lyrics, think, bpm, keyscale, etc.). Uses in-process acestep (LLMHandler for metadata, DiT for audio). urls: - https://github.com/ace-step/ACE-Step-1.5 tags: - music-generation - sound-generation capabilities: amd: rocm-ace-step default: cpu-ace-step intel: intel-ace-step metal: metal-ace-step nvidia: cuda12-ace-step nvidia-cuda-12: cuda12-ace-step nvidia-cuda-13: cuda13-ace-step uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-ace-step mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-ace-step - name: cuda13-ace-step alias: ace-step description: | ACE-Step 1.5 is an open-source music generation model. It supports simple mode (natural language description) and advanced mode (caption, lyrics, think, bpm, keyscale, etc.). Uses in-process acestep (LLMHandler for metadata, DiT for audio). urls: - https://github.com/ace-step/ACE-Step-1.5 tags: - music-generation - sound-generation capabilities: amd: rocm-ace-step default: cpu-ace-step intel: intel-ace-step metal: metal-ace-step nvidia: cuda12-ace-step nvidia-cuda-12: cuda12-ace-step nvidia-cuda-13: cuda13-ace-step uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-ace-step mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-ace-step - name: cuda13-ace-step-development alias: ace-step description: | ACE-Step 1.5 is an open-source music generation model. It supports simple mode (natural language description) and advanced mode (caption, lyrics, think, bpm, keyscale, etc.). Uses in-process acestep (LLMHandler for metadata, DiT for audio). urls: - https://github.com/ace-step/ACE-Step-1.5 tags: - music-generation - sound-generation capabilities: amd: rocm-ace-step default: cpu-ace-step intel: intel-ace-step metal: metal-ace-step nvidia: cuda12-ace-step nvidia-cuda-12: cuda12-ace-step nvidia-cuda-13: cuda13-ace-step uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-ace-step mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-ace-step - name: rocm-ace-step alias: ace-step description: | ACE-Step 1.5 is an open-source music generation model. It supports simple mode (natural language description) and advanced mode (caption, lyrics, think, bpm, keyscale, etc.). Uses in-process acestep (LLMHandler for metadata, DiT for audio). urls: - https://github.com/ace-step/ACE-Step-1.5 tags: - music-generation - sound-generation capabilities: amd: rocm-ace-step default: cpu-ace-step intel: intel-ace-step metal: metal-ace-step nvidia: cuda12-ace-step nvidia-cuda-12: cuda12-ace-step nvidia-cuda-13: cuda13-ace-step uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-ace-step mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-ace-step - name: rocm-ace-step-development alias: ace-step description: | ACE-Step 1.5 is an open-source music generation model. It supports simple mode (natural language description) and advanced mode (caption, lyrics, think, bpm, keyscale, etc.). Uses in-process acestep (LLMHandler for metadata, DiT for audio). urls: - https://github.com/ace-step/ACE-Step-1.5 tags: - music-generation - sound-generation capabilities: amd: rocm-ace-step default: cpu-ace-step intel: intel-ace-step metal: metal-ace-step nvidia: cuda12-ace-step nvidia-cuda-12: cuda12-ace-step nvidia-cuda-13: cuda13-ace-step uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-ace-step mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-ace-step - name: intel-ace-step alias: ace-step description: | ACE-Step 1.5 is an open-source music generation model. It supports simple mode (natural language description) and advanced mode (caption, lyrics, think, bpm, keyscale, etc.). Uses in-process acestep (LLMHandler for metadata, DiT for audio). urls: - https://github.com/ace-step/ACE-Step-1.5 tags: - music-generation - sound-generation capabilities: amd: rocm-ace-step default: cpu-ace-step intel: intel-ace-step metal: metal-ace-step nvidia: cuda12-ace-step nvidia-cuda-12: cuda12-ace-step nvidia-cuda-13: cuda13-ace-step uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-ace-step mirrors: - localai/localai-backends:latest-gpu-intel-ace-step - name: intel-ace-step-development alias: ace-step description: | ACE-Step 1.5 is an open-source music generation model. It supports simple mode (natural language description) and advanced mode (caption, lyrics, think, bpm, keyscale, etc.). Uses in-process acestep (LLMHandler for metadata, DiT for audio). urls: - https://github.com/ace-step/ACE-Step-1.5 tags: - music-generation - sound-generation capabilities: amd: rocm-ace-step default: cpu-ace-step intel: intel-ace-step metal: metal-ace-step nvidia: cuda12-ace-step nvidia-cuda-12: cuda12-ace-step nvidia-cuda-13: cuda13-ace-step uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-ace-step mirrors: - localai/localai-backends:master-gpu-intel-ace-step - name: metal-ace-step alias: ace-step description: | ACE-Step 1.5 is an open-source music generation model. It supports simple mode (natural language description) and advanced mode (caption, lyrics, think, bpm, keyscale, etc.). Uses in-process acestep (LLMHandler for metadata, DiT for audio). urls: - https://github.com/ace-step/ACE-Step-1.5 tags: - music-generation - sound-generation capabilities: amd: rocm-ace-step default: cpu-ace-step intel: intel-ace-step metal: metal-ace-step nvidia: cuda12-ace-step nvidia-cuda-12: cuda12-ace-step nvidia-cuda-13: cuda13-ace-step uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-ace-step mirrors: - localai/localai-backends:latest-metal-darwin-arm64-ace-step - name: metal-ace-step-development alias: ace-step description: | ACE-Step 1.5 is an open-source music generation model. It supports simple mode (natural language description) and advanced mode (caption, lyrics, think, bpm, keyscale, etc.). Uses in-process acestep (LLMHandler for metadata, DiT for audio). urls: - https://github.com/ace-step/ACE-Step-1.5 tags: - music-generation - sound-generation capabilities: amd: rocm-ace-step default: cpu-ace-step intel: intel-ace-step metal: metal-ace-step nvidia: cuda12-ace-step nvidia-cuda-12: cuda12-ace-step nvidia-cuda-13: cuda13-ace-step uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-ace-step mirrors: - localai/localai-backends:master-metal-darwin-arm64-ace-step - name: nvidia-l4t-arm64-acestep-cpp alias: acestep-cpp description: | ACE-Step 1.5 C++ backend using GGML. Native C++ implementation of ACE-Step music generation with GPU support through GGML backends. Generates stereo 48kHz audio from text descriptions and optional lyrics via a two-stage pipeline: text-to-code (ace-qwen3 LLM) + code-to-audio (DiT-VAE). urls: - https://github.com/ace-step/acestep.cpp tags: - music-generation - sound-generation capabilities: amd: rocm-acestep-cpp default: cpu-acestep-cpp intel: intel-sycl-f16-acestep-cpp metal: metal-acestep-cpp nvidia: cuda12-acestep-cpp nvidia-cuda-12: cuda12-acestep-cpp nvidia-cuda-13: cuda13-acestep-cpp nvidia-l4t: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-acestep-cpp vulkan: vulkan-acestep-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-acestep-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-arm64-acestep-cpp - name: nvidia-l4t-arm64-acestep-cpp-development alias: acestep-cpp description: | ACE-Step 1.5 C++ backend using GGML. Native C++ implementation of ACE-Step music generation with GPU support through GGML backends. Generates stereo 48kHz audio from text descriptions and optional lyrics via a two-stage pipeline: text-to-code (ace-qwen3 LLM) + code-to-audio (DiT-VAE). urls: - https://github.com/ace-step/acestep.cpp tags: - music-generation - sound-generation capabilities: amd: rocm-acestep-cpp default: cpu-acestep-cpp intel: intel-sycl-f16-acestep-cpp metal: metal-acestep-cpp nvidia: cuda12-acestep-cpp nvidia-cuda-12: cuda12-acestep-cpp nvidia-cuda-13: cuda13-acestep-cpp nvidia-l4t: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-acestep-cpp vulkan: vulkan-acestep-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-acestep-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-arm64-acestep-cpp - name: cuda13-nvidia-l4t-arm64-acestep-cpp alias: acestep-cpp description: | ACE-Step 1.5 C++ backend using GGML. Native C++ implementation of ACE-Step music generation with GPU support through GGML backends. Generates stereo 48kHz audio from text descriptions and optional lyrics via a two-stage pipeline: text-to-code (ace-qwen3 LLM) + code-to-audio (DiT-VAE). urls: - https://github.com/ace-step/acestep.cpp tags: - music-generation - sound-generation capabilities: amd: rocm-acestep-cpp default: cpu-acestep-cpp intel: intel-sycl-f16-acestep-cpp metal: metal-acestep-cpp nvidia: cuda12-acestep-cpp nvidia-cuda-12: cuda12-acestep-cpp nvidia-cuda-13: cuda13-acestep-cpp nvidia-l4t: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-acestep-cpp vulkan: vulkan-acestep-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-acestep-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-acestep-cpp - name: cuda13-nvidia-l4t-arm64-acestep-cpp-development alias: acestep-cpp description: | ACE-Step 1.5 C++ backend using GGML. Native C++ implementation of ACE-Step music generation with GPU support through GGML backends. Generates stereo 48kHz audio from text descriptions and optional lyrics via a two-stage pipeline: text-to-code (ace-qwen3 LLM) + code-to-audio (DiT-VAE). urls: - https://github.com/ace-step/acestep.cpp tags: - music-generation - sound-generation capabilities: amd: rocm-acestep-cpp default: cpu-acestep-cpp intel: intel-sycl-f16-acestep-cpp metal: metal-acestep-cpp nvidia: cuda12-acestep-cpp nvidia-cuda-12: cuda12-acestep-cpp nvidia-cuda-13: cuda13-acestep-cpp nvidia-l4t: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-acestep-cpp vulkan: vulkan-acestep-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-acestep-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-acestep-cpp - name: cpu-acestep-cpp alias: acestep-cpp description: | ACE-Step 1.5 C++ backend using GGML. Native C++ implementation of ACE-Step music generation with GPU support through GGML backends. Generates stereo 48kHz audio from text descriptions and optional lyrics via a two-stage pipeline: text-to-code (ace-qwen3 LLM) + code-to-audio (DiT-VAE). urls: - https://github.com/ace-step/acestep.cpp tags: - music-generation - sound-generation capabilities: amd: rocm-acestep-cpp default: cpu-acestep-cpp intel: intel-sycl-f16-acestep-cpp metal: metal-acestep-cpp nvidia: cuda12-acestep-cpp nvidia-cuda-12: cuda12-acestep-cpp nvidia-cuda-13: cuda13-acestep-cpp nvidia-l4t: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-acestep-cpp vulkan: vulkan-acestep-cpp uri: quay.io/go-skynet/local-ai-backends:latest-cpu-acestep-cpp mirrors: - localai/localai-backends:latest-cpu-acestep-cpp - name: metal-acestep-cpp alias: acestep-cpp description: | ACE-Step 1.5 C++ backend using GGML. Native C++ implementation of ACE-Step music generation with GPU support through GGML backends. Generates stereo 48kHz audio from text descriptions and optional lyrics via a two-stage pipeline: text-to-code (ace-qwen3 LLM) + code-to-audio (DiT-VAE). urls: - https://github.com/ace-step/acestep.cpp tags: - music-generation - sound-generation capabilities: amd: rocm-acestep-cpp default: cpu-acestep-cpp intel: intel-sycl-f16-acestep-cpp metal: metal-acestep-cpp nvidia: cuda12-acestep-cpp nvidia-cuda-12: cuda12-acestep-cpp nvidia-cuda-13: cuda13-acestep-cpp nvidia-l4t: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-acestep-cpp vulkan: vulkan-acestep-cpp uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-acestep-cpp mirrors: - localai/localai-backends:latest-metal-darwin-arm64-acestep-cpp - name: metal-acestep-cpp-development alias: acestep-cpp description: | ACE-Step 1.5 C++ backend using GGML. Native C++ implementation of ACE-Step music generation with GPU support through GGML backends. Generates stereo 48kHz audio from text descriptions and optional lyrics via a two-stage pipeline: text-to-code (ace-qwen3 LLM) + code-to-audio (DiT-VAE). urls: - https://github.com/ace-step/acestep.cpp tags: - music-generation - sound-generation capabilities: amd: rocm-acestep-cpp default: cpu-acestep-cpp intel: intel-sycl-f16-acestep-cpp metal: metal-acestep-cpp nvidia: cuda12-acestep-cpp nvidia-cuda-12: cuda12-acestep-cpp nvidia-cuda-13: cuda13-acestep-cpp nvidia-l4t: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-acestep-cpp vulkan: vulkan-acestep-cpp uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-acestep-cpp mirrors: - localai/localai-backends:master-metal-darwin-arm64-acestep-cpp - name: cpu-acestep-cpp-development alias: acestep-cpp description: | ACE-Step 1.5 C++ backend using GGML. Native C++ implementation of ACE-Step music generation with GPU support through GGML backends. Generates stereo 48kHz audio from text descriptions and optional lyrics via a two-stage pipeline: text-to-code (ace-qwen3 LLM) + code-to-audio (DiT-VAE). urls: - https://github.com/ace-step/acestep.cpp tags: - music-generation - sound-generation capabilities: amd: rocm-acestep-cpp default: cpu-acestep-cpp intel: intel-sycl-f16-acestep-cpp metal: metal-acestep-cpp nvidia: cuda12-acestep-cpp nvidia-cuda-12: cuda12-acestep-cpp nvidia-cuda-13: cuda13-acestep-cpp nvidia-l4t: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-acestep-cpp vulkan: vulkan-acestep-cpp uri: quay.io/go-skynet/local-ai-backends:master-cpu-acestep-cpp mirrors: - localai/localai-backends:master-cpu-acestep-cpp - name: cuda12-acestep-cpp alias: acestep-cpp description: | ACE-Step 1.5 C++ backend using GGML. Native C++ implementation of ACE-Step music generation with GPU support through GGML backends. Generates stereo 48kHz audio from text descriptions and optional lyrics via a two-stage pipeline: text-to-code (ace-qwen3 LLM) + code-to-audio (DiT-VAE). urls: - https://github.com/ace-step/acestep.cpp tags: - music-generation - sound-generation capabilities: amd: rocm-acestep-cpp default: cpu-acestep-cpp intel: intel-sycl-f16-acestep-cpp metal: metal-acestep-cpp nvidia: cuda12-acestep-cpp nvidia-cuda-12: cuda12-acestep-cpp nvidia-cuda-13: cuda13-acestep-cpp nvidia-l4t: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-acestep-cpp vulkan: vulkan-acestep-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-acestep-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-acestep-cpp - name: rocm-acestep-cpp alias: acestep-cpp description: | ACE-Step 1.5 C++ backend using GGML. Native C++ implementation of ACE-Step music generation with GPU support through GGML backends. Generates stereo 48kHz audio from text descriptions and optional lyrics via a two-stage pipeline: text-to-code (ace-qwen3 LLM) + code-to-audio (DiT-VAE). urls: - https://github.com/ace-step/acestep.cpp tags: - music-generation - sound-generation capabilities: amd: rocm-acestep-cpp default: cpu-acestep-cpp intel: intel-sycl-f16-acestep-cpp metal: metal-acestep-cpp nvidia: cuda12-acestep-cpp nvidia-cuda-12: cuda12-acestep-cpp nvidia-cuda-13: cuda13-acestep-cpp nvidia-l4t: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-acestep-cpp vulkan: vulkan-acestep-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-acestep-cpp mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-acestep-cpp - name: intel-sycl-f32-acestep-cpp alias: acestep-cpp description: | ACE-Step 1.5 C++ backend using GGML. Native C++ implementation of ACE-Step music generation with GPU support through GGML backends. Generates stereo 48kHz audio from text descriptions and optional lyrics via a two-stage pipeline: text-to-code (ace-qwen3 LLM) + code-to-audio (DiT-VAE). urls: - https://github.com/ace-step/acestep.cpp tags: - music-generation - sound-generation capabilities: amd: rocm-acestep-cpp default: cpu-acestep-cpp intel: intel-sycl-f16-acestep-cpp metal: metal-acestep-cpp nvidia: cuda12-acestep-cpp nvidia-cuda-12: cuda12-acestep-cpp nvidia-cuda-13: cuda13-acestep-cpp nvidia-l4t: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-acestep-cpp vulkan: vulkan-acestep-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-acestep-cpp mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f32-acestep-cpp - name: intel-sycl-f16-acestep-cpp alias: acestep-cpp description: | ACE-Step 1.5 C++ backend using GGML. Native C++ implementation of ACE-Step music generation with GPU support through GGML backends. Generates stereo 48kHz audio from text descriptions and optional lyrics via a two-stage pipeline: text-to-code (ace-qwen3 LLM) + code-to-audio (DiT-VAE). urls: - https://github.com/ace-step/acestep.cpp tags: - music-generation - sound-generation capabilities: amd: rocm-acestep-cpp default: cpu-acestep-cpp intel: intel-sycl-f16-acestep-cpp metal: metal-acestep-cpp nvidia: cuda12-acestep-cpp nvidia-cuda-12: cuda12-acestep-cpp nvidia-cuda-13: cuda13-acestep-cpp nvidia-l4t: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-acestep-cpp vulkan: vulkan-acestep-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-acestep-cpp mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f16-acestep-cpp - name: vulkan-acestep-cpp alias: acestep-cpp description: | ACE-Step 1.5 C++ backend using GGML. Native C++ implementation of ACE-Step music generation with GPU support through GGML backends. Generates stereo 48kHz audio from text descriptions and optional lyrics via a two-stage pipeline: text-to-code (ace-qwen3 LLM) + code-to-audio (DiT-VAE). urls: - https://github.com/ace-step/acestep.cpp tags: - music-generation - sound-generation capabilities: amd: rocm-acestep-cpp default: cpu-acestep-cpp intel: intel-sycl-f16-acestep-cpp metal: metal-acestep-cpp nvidia: cuda12-acestep-cpp nvidia-cuda-12: cuda12-acestep-cpp nvidia-cuda-13: cuda13-acestep-cpp nvidia-l4t: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-acestep-cpp vulkan: vulkan-acestep-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-acestep-cpp mirrors: - localai/localai-backends:latest-gpu-vulkan-acestep-cpp - name: vulkan-acestep-cpp-development alias: acestep-cpp description: | ACE-Step 1.5 C++ backend using GGML. Native C++ implementation of ACE-Step music generation with GPU support through GGML backends. Generates stereo 48kHz audio from text descriptions and optional lyrics via a two-stage pipeline: text-to-code (ace-qwen3 LLM) + code-to-audio (DiT-VAE). urls: - https://github.com/ace-step/acestep.cpp tags: - music-generation - sound-generation capabilities: amd: rocm-acestep-cpp default: cpu-acestep-cpp intel: intel-sycl-f16-acestep-cpp metal: metal-acestep-cpp nvidia: cuda12-acestep-cpp nvidia-cuda-12: cuda12-acestep-cpp nvidia-cuda-13: cuda13-acestep-cpp nvidia-l4t: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-acestep-cpp vulkan: vulkan-acestep-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-acestep-cpp mirrors: - localai/localai-backends:master-gpu-vulkan-acestep-cpp - name: cuda12-acestep-cpp-development alias: acestep-cpp description: | ACE-Step 1.5 C++ backend using GGML. Native C++ implementation of ACE-Step music generation with GPU support through GGML backends. Generates stereo 48kHz audio from text descriptions and optional lyrics via a two-stage pipeline: text-to-code (ace-qwen3 LLM) + code-to-audio (DiT-VAE). urls: - https://github.com/ace-step/acestep.cpp tags: - music-generation - sound-generation capabilities: amd: rocm-acestep-cpp default: cpu-acestep-cpp intel: intel-sycl-f16-acestep-cpp metal: metal-acestep-cpp nvidia: cuda12-acestep-cpp nvidia-cuda-12: cuda12-acestep-cpp nvidia-cuda-13: cuda13-acestep-cpp nvidia-l4t: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-acestep-cpp vulkan: vulkan-acestep-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-acestep-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-acestep-cpp - name: rocm-acestep-cpp-development alias: acestep-cpp description: | ACE-Step 1.5 C++ backend using GGML. Native C++ implementation of ACE-Step music generation with GPU support through GGML backends. Generates stereo 48kHz audio from text descriptions and optional lyrics via a two-stage pipeline: text-to-code (ace-qwen3 LLM) + code-to-audio (DiT-VAE). urls: - https://github.com/ace-step/acestep.cpp tags: - music-generation - sound-generation capabilities: amd: rocm-acestep-cpp default: cpu-acestep-cpp intel: intel-sycl-f16-acestep-cpp metal: metal-acestep-cpp nvidia: cuda12-acestep-cpp nvidia-cuda-12: cuda12-acestep-cpp nvidia-cuda-13: cuda13-acestep-cpp nvidia-l4t: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-acestep-cpp vulkan: vulkan-acestep-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-acestep-cpp mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-acestep-cpp - name: intel-sycl-f32-acestep-cpp-development alias: acestep-cpp description: | ACE-Step 1.5 C++ backend using GGML. Native C++ implementation of ACE-Step music generation with GPU support through GGML backends. Generates stereo 48kHz audio from text descriptions and optional lyrics via a two-stage pipeline: text-to-code (ace-qwen3 LLM) + code-to-audio (DiT-VAE). urls: - https://github.com/ace-step/acestep.cpp tags: - music-generation - sound-generation capabilities: amd: rocm-acestep-cpp default: cpu-acestep-cpp intel: intel-sycl-f16-acestep-cpp metal: metal-acestep-cpp nvidia: cuda12-acestep-cpp nvidia-cuda-12: cuda12-acestep-cpp nvidia-cuda-13: cuda13-acestep-cpp nvidia-l4t: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-acestep-cpp vulkan: vulkan-acestep-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-acestep-cpp mirrors: - localai/localai-backends:master-gpu-intel-sycl-f32-acestep-cpp - name: intel-sycl-f16-acestep-cpp-development alias: acestep-cpp description: | ACE-Step 1.5 C++ backend using GGML. Native C++ implementation of ACE-Step music generation with GPU support through GGML backends. Generates stereo 48kHz audio from text descriptions and optional lyrics via a two-stage pipeline: text-to-code (ace-qwen3 LLM) + code-to-audio (DiT-VAE). urls: - https://github.com/ace-step/acestep.cpp tags: - music-generation - sound-generation capabilities: amd: rocm-acestep-cpp default: cpu-acestep-cpp intel: intel-sycl-f16-acestep-cpp metal: metal-acestep-cpp nvidia: cuda12-acestep-cpp nvidia-cuda-12: cuda12-acestep-cpp nvidia-cuda-13: cuda13-acestep-cpp nvidia-l4t: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-acestep-cpp vulkan: vulkan-acestep-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-acestep-cpp mirrors: - localai/localai-backends:master-gpu-intel-sycl-f16-acestep-cpp - name: cuda13-acestep-cpp alias: acestep-cpp description: | ACE-Step 1.5 C++ backend using GGML. Native C++ implementation of ACE-Step music generation with GPU support through GGML backends. Generates stereo 48kHz audio from text descriptions and optional lyrics via a two-stage pipeline: text-to-code (ace-qwen3 LLM) + code-to-audio (DiT-VAE). urls: - https://github.com/ace-step/acestep.cpp tags: - music-generation - sound-generation capabilities: amd: rocm-acestep-cpp default: cpu-acestep-cpp intel: intel-sycl-f16-acestep-cpp metal: metal-acestep-cpp nvidia: cuda12-acestep-cpp nvidia-cuda-12: cuda12-acestep-cpp nvidia-cuda-13: cuda13-acestep-cpp nvidia-l4t: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-acestep-cpp vulkan: vulkan-acestep-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-acestep-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-acestep-cpp - name: cuda13-acestep-cpp-development alias: acestep-cpp description: | ACE-Step 1.5 C++ backend using GGML. Native C++ implementation of ACE-Step music generation with GPU support through GGML backends. Generates stereo 48kHz audio from text descriptions and optional lyrics via a two-stage pipeline: text-to-code (ace-qwen3 LLM) + code-to-audio (DiT-VAE). urls: - https://github.com/ace-step/acestep.cpp tags: - music-generation - sound-generation capabilities: amd: rocm-acestep-cpp default: cpu-acestep-cpp intel: intel-sycl-f16-acestep-cpp metal: metal-acestep-cpp nvidia: cuda12-acestep-cpp nvidia-cuda-12: cuda12-acestep-cpp nvidia-cuda-13: cuda13-acestep-cpp nvidia-l4t: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-acestep-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-acestep-cpp vulkan: vulkan-acestep-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-acestep-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-acestep-cpp - name: nvidia-l4t-arm64-qwen3-tts-cpp alias: qwen3-tts-cpp description: | Qwen3-TTS C++ backend using GGML (qwentts.cpp). Native C++ text-to-speech with streaming output, named speakers, voice design, and zero-shot voice cloning. 24kHz mono, 11 languages with Mandarin dialects. 0.6B and 1.7B models in Q8_0 / Q4_K_M. urls: - https://github.com/ServeurpersoCom/qwentts.cpp tags: - text-to-speech - tts - voice-cloning - streaming capabilities: amd: rocm-qwen3-tts-cpp default: cpu-qwen3-tts-cpp intel: intel-sycl-f16-qwen3-tts-cpp metal: metal-qwen3-tts-cpp nvidia: cuda12-qwen3-tts-cpp nvidia-cuda-12: cuda12-qwen3-tts-cpp nvidia-cuda-13: cuda13-qwen3-tts-cpp nvidia-l4t: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen3-tts-cpp vulkan: vulkan-qwen3-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-qwen3-tts-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-arm64-qwen3-tts-cpp - name: nvidia-l4t-arm64-qwen3-tts-cpp-development alias: qwen3-tts-cpp description: | Qwen3-TTS C++ backend using GGML (qwentts.cpp). Native C++ text-to-speech with streaming output, named speakers, voice design, and zero-shot voice cloning. 24kHz mono, 11 languages with Mandarin dialects. 0.6B and 1.7B models in Q8_0 / Q4_K_M. urls: - https://github.com/ServeurpersoCom/qwentts.cpp tags: - text-to-speech - tts - voice-cloning - streaming capabilities: amd: rocm-qwen3-tts-cpp default: cpu-qwen3-tts-cpp intel: intel-sycl-f16-qwen3-tts-cpp metal: metal-qwen3-tts-cpp nvidia: cuda12-qwen3-tts-cpp nvidia-cuda-12: cuda12-qwen3-tts-cpp nvidia-cuda-13: cuda13-qwen3-tts-cpp nvidia-l4t: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen3-tts-cpp vulkan: vulkan-qwen3-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-qwen3-tts-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-arm64-qwen3-tts-cpp - name: cuda13-nvidia-l4t-arm64-qwen3-tts-cpp alias: qwen3-tts-cpp description: | Qwen3-TTS C++ backend using GGML (qwentts.cpp). Native C++ text-to-speech with streaming output, named speakers, voice design, and zero-shot voice cloning. 24kHz mono, 11 languages with Mandarin dialects. 0.6B and 1.7B models in Q8_0 / Q4_K_M. urls: - https://github.com/ServeurpersoCom/qwentts.cpp tags: - text-to-speech - tts - voice-cloning - streaming capabilities: amd: rocm-qwen3-tts-cpp default: cpu-qwen3-tts-cpp intel: intel-sycl-f16-qwen3-tts-cpp metal: metal-qwen3-tts-cpp nvidia: cuda12-qwen3-tts-cpp nvidia-cuda-12: cuda12-qwen3-tts-cpp nvidia-cuda-13: cuda13-qwen3-tts-cpp nvidia-l4t: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen3-tts-cpp vulkan: vulkan-qwen3-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-qwen3-tts-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-qwen3-tts-cpp - name: cuda13-nvidia-l4t-arm64-qwen3-tts-cpp-development alias: qwen3-tts-cpp description: | Qwen3-TTS C++ backend using GGML (qwentts.cpp). Native C++ text-to-speech with streaming output, named speakers, voice design, and zero-shot voice cloning. 24kHz mono, 11 languages with Mandarin dialects. 0.6B and 1.7B models in Q8_0 / Q4_K_M. urls: - https://github.com/ServeurpersoCom/qwentts.cpp tags: - text-to-speech - tts - voice-cloning - streaming capabilities: amd: rocm-qwen3-tts-cpp default: cpu-qwen3-tts-cpp intel: intel-sycl-f16-qwen3-tts-cpp metal: metal-qwen3-tts-cpp nvidia: cuda12-qwen3-tts-cpp nvidia-cuda-12: cuda12-qwen3-tts-cpp nvidia-cuda-13: cuda13-qwen3-tts-cpp nvidia-l4t: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen3-tts-cpp vulkan: vulkan-qwen3-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-qwen3-tts-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-qwen3-tts-cpp - name: cpu-qwen3-tts-cpp alias: qwen3-tts-cpp description: | Qwen3-TTS C++ backend using GGML (qwentts.cpp). Native C++ text-to-speech with streaming output, named speakers, voice design, and zero-shot voice cloning. 24kHz mono, 11 languages with Mandarin dialects. 0.6B and 1.7B models in Q8_0 / Q4_K_M. urls: - https://github.com/ServeurpersoCom/qwentts.cpp tags: - text-to-speech - tts - voice-cloning - streaming capabilities: amd: rocm-qwen3-tts-cpp default: cpu-qwen3-tts-cpp intel: intel-sycl-f16-qwen3-tts-cpp metal: metal-qwen3-tts-cpp nvidia: cuda12-qwen3-tts-cpp nvidia-cuda-12: cuda12-qwen3-tts-cpp nvidia-cuda-13: cuda13-qwen3-tts-cpp nvidia-l4t: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen3-tts-cpp vulkan: vulkan-qwen3-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-cpu-qwen3-tts-cpp mirrors: - localai/localai-backends:latest-cpu-qwen3-tts-cpp - name: metal-qwen3-tts-cpp alias: qwen3-tts-cpp description: | Qwen3-TTS C++ backend using GGML (qwentts.cpp). Native C++ text-to-speech with streaming output, named speakers, voice design, and zero-shot voice cloning. 24kHz mono, 11 languages with Mandarin dialects. 0.6B and 1.7B models in Q8_0 / Q4_K_M. urls: - https://github.com/ServeurpersoCom/qwentts.cpp tags: - text-to-speech - tts - voice-cloning - streaming capabilities: amd: rocm-qwen3-tts-cpp default: cpu-qwen3-tts-cpp intel: intel-sycl-f16-qwen3-tts-cpp metal: metal-qwen3-tts-cpp nvidia: cuda12-qwen3-tts-cpp nvidia-cuda-12: cuda12-qwen3-tts-cpp nvidia-cuda-13: cuda13-qwen3-tts-cpp nvidia-l4t: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen3-tts-cpp vulkan: vulkan-qwen3-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-qwen3-tts-cpp mirrors: - localai/localai-backends:latest-metal-darwin-arm64-qwen3-tts-cpp - name: metal-qwen3-tts-cpp-development alias: qwen3-tts-cpp description: | Qwen3-TTS C++ backend using GGML (qwentts.cpp). Native C++ text-to-speech with streaming output, named speakers, voice design, and zero-shot voice cloning. 24kHz mono, 11 languages with Mandarin dialects. 0.6B and 1.7B models in Q8_0 / Q4_K_M. urls: - https://github.com/ServeurpersoCom/qwentts.cpp tags: - text-to-speech - tts - voice-cloning - streaming capabilities: amd: rocm-qwen3-tts-cpp default: cpu-qwen3-tts-cpp intel: intel-sycl-f16-qwen3-tts-cpp metal: metal-qwen3-tts-cpp nvidia: cuda12-qwen3-tts-cpp nvidia-cuda-12: cuda12-qwen3-tts-cpp nvidia-cuda-13: cuda13-qwen3-tts-cpp nvidia-l4t: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen3-tts-cpp vulkan: vulkan-qwen3-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-qwen3-tts-cpp mirrors: - localai/localai-backends:master-metal-darwin-arm64-qwen3-tts-cpp - name: cpu-qwen3-tts-cpp-development alias: qwen3-tts-cpp description: | Qwen3-TTS C++ backend using GGML (qwentts.cpp). Native C++ text-to-speech with streaming output, named speakers, voice design, and zero-shot voice cloning. 24kHz mono, 11 languages with Mandarin dialects. 0.6B and 1.7B models in Q8_0 / Q4_K_M. urls: - https://github.com/ServeurpersoCom/qwentts.cpp tags: - text-to-speech - tts - voice-cloning - streaming capabilities: amd: rocm-qwen3-tts-cpp default: cpu-qwen3-tts-cpp intel: intel-sycl-f16-qwen3-tts-cpp metal: metal-qwen3-tts-cpp nvidia: cuda12-qwen3-tts-cpp nvidia-cuda-12: cuda12-qwen3-tts-cpp nvidia-cuda-13: cuda13-qwen3-tts-cpp nvidia-l4t: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen3-tts-cpp vulkan: vulkan-qwen3-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-cpu-qwen3-tts-cpp mirrors: - localai/localai-backends:master-cpu-qwen3-tts-cpp - name: cuda12-qwen3-tts-cpp alias: qwen3-tts-cpp description: | Qwen3-TTS C++ backend using GGML (qwentts.cpp). Native C++ text-to-speech with streaming output, named speakers, voice design, and zero-shot voice cloning. 24kHz mono, 11 languages with Mandarin dialects. 0.6B and 1.7B models in Q8_0 / Q4_K_M. urls: - https://github.com/ServeurpersoCom/qwentts.cpp tags: - text-to-speech - tts - voice-cloning - streaming capabilities: amd: rocm-qwen3-tts-cpp default: cpu-qwen3-tts-cpp intel: intel-sycl-f16-qwen3-tts-cpp metal: metal-qwen3-tts-cpp nvidia: cuda12-qwen3-tts-cpp nvidia-cuda-12: cuda12-qwen3-tts-cpp nvidia-cuda-13: cuda13-qwen3-tts-cpp nvidia-l4t: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen3-tts-cpp vulkan: vulkan-qwen3-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-qwen3-tts-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-qwen3-tts-cpp - name: rocm-qwen3-tts-cpp alias: qwen3-tts-cpp description: | Qwen3-TTS C++ backend using GGML (qwentts.cpp). Native C++ text-to-speech with streaming output, named speakers, voice design, and zero-shot voice cloning. 24kHz mono, 11 languages with Mandarin dialects. 0.6B and 1.7B models in Q8_0 / Q4_K_M. urls: - https://github.com/ServeurpersoCom/qwentts.cpp tags: - text-to-speech - tts - voice-cloning - streaming capabilities: amd: rocm-qwen3-tts-cpp default: cpu-qwen3-tts-cpp intel: intel-sycl-f16-qwen3-tts-cpp metal: metal-qwen3-tts-cpp nvidia: cuda12-qwen3-tts-cpp nvidia-cuda-12: cuda12-qwen3-tts-cpp nvidia-cuda-13: cuda13-qwen3-tts-cpp nvidia-l4t: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen3-tts-cpp vulkan: vulkan-qwen3-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-qwen3-tts-cpp mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-qwen3-tts-cpp - name: intel-sycl-f32-qwen3-tts-cpp alias: qwen3-tts-cpp description: | Qwen3-TTS C++ backend using GGML (qwentts.cpp). Native C++ text-to-speech with streaming output, named speakers, voice design, and zero-shot voice cloning. 24kHz mono, 11 languages with Mandarin dialects. 0.6B and 1.7B models in Q8_0 / Q4_K_M. urls: - https://github.com/ServeurpersoCom/qwentts.cpp tags: - text-to-speech - tts - voice-cloning - streaming capabilities: amd: rocm-qwen3-tts-cpp default: cpu-qwen3-tts-cpp intel: intel-sycl-f16-qwen3-tts-cpp metal: metal-qwen3-tts-cpp nvidia: cuda12-qwen3-tts-cpp nvidia-cuda-12: cuda12-qwen3-tts-cpp nvidia-cuda-13: cuda13-qwen3-tts-cpp nvidia-l4t: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen3-tts-cpp vulkan: vulkan-qwen3-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-qwen3-tts-cpp mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f32-qwen3-tts-cpp - name: intel-sycl-f16-qwen3-tts-cpp alias: qwen3-tts-cpp description: | Qwen3-TTS C++ backend using GGML (qwentts.cpp). Native C++ text-to-speech with streaming output, named speakers, voice design, and zero-shot voice cloning. 24kHz mono, 11 languages with Mandarin dialects. 0.6B and 1.7B models in Q8_0 / Q4_K_M. urls: - https://github.com/ServeurpersoCom/qwentts.cpp tags: - text-to-speech - tts - voice-cloning - streaming capabilities: amd: rocm-qwen3-tts-cpp default: cpu-qwen3-tts-cpp intel: intel-sycl-f16-qwen3-tts-cpp metal: metal-qwen3-tts-cpp nvidia: cuda12-qwen3-tts-cpp nvidia-cuda-12: cuda12-qwen3-tts-cpp nvidia-cuda-13: cuda13-qwen3-tts-cpp nvidia-l4t: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen3-tts-cpp vulkan: vulkan-qwen3-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-qwen3-tts-cpp mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f16-qwen3-tts-cpp - name: vulkan-qwen3-tts-cpp alias: qwen3-tts-cpp description: | Qwen3-TTS C++ backend using GGML (qwentts.cpp). Native C++ text-to-speech with streaming output, named speakers, voice design, and zero-shot voice cloning. 24kHz mono, 11 languages with Mandarin dialects. 0.6B and 1.7B models in Q8_0 / Q4_K_M. urls: - https://github.com/ServeurpersoCom/qwentts.cpp tags: - text-to-speech - tts - voice-cloning - streaming capabilities: amd: rocm-qwen3-tts-cpp default: cpu-qwen3-tts-cpp intel: intel-sycl-f16-qwen3-tts-cpp metal: metal-qwen3-tts-cpp nvidia: cuda12-qwen3-tts-cpp nvidia-cuda-12: cuda12-qwen3-tts-cpp nvidia-cuda-13: cuda13-qwen3-tts-cpp nvidia-l4t: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen3-tts-cpp vulkan: vulkan-qwen3-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-qwen3-tts-cpp mirrors: - localai/localai-backends:latest-gpu-vulkan-qwen3-tts-cpp - name: vulkan-qwen3-tts-cpp-development alias: qwen3-tts-cpp description: | Qwen3-TTS C++ backend using GGML (qwentts.cpp). Native C++ text-to-speech with streaming output, named speakers, voice design, and zero-shot voice cloning. 24kHz mono, 11 languages with Mandarin dialects. 0.6B and 1.7B models in Q8_0 / Q4_K_M. urls: - https://github.com/ServeurpersoCom/qwentts.cpp tags: - text-to-speech - tts - voice-cloning - streaming capabilities: amd: rocm-qwen3-tts-cpp default: cpu-qwen3-tts-cpp intel: intel-sycl-f16-qwen3-tts-cpp metal: metal-qwen3-tts-cpp nvidia: cuda12-qwen3-tts-cpp nvidia-cuda-12: cuda12-qwen3-tts-cpp nvidia-cuda-13: cuda13-qwen3-tts-cpp nvidia-l4t: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen3-tts-cpp vulkan: vulkan-qwen3-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-qwen3-tts-cpp mirrors: - localai/localai-backends:master-gpu-vulkan-qwen3-tts-cpp - name: cuda12-qwen3-tts-cpp-development alias: qwen3-tts-cpp description: | Qwen3-TTS C++ backend using GGML (qwentts.cpp). Native C++ text-to-speech with streaming output, named speakers, voice design, and zero-shot voice cloning. 24kHz mono, 11 languages with Mandarin dialects. 0.6B and 1.7B models in Q8_0 / Q4_K_M. urls: - https://github.com/ServeurpersoCom/qwentts.cpp tags: - text-to-speech - tts - voice-cloning - streaming capabilities: amd: rocm-qwen3-tts-cpp default: cpu-qwen3-tts-cpp intel: intel-sycl-f16-qwen3-tts-cpp metal: metal-qwen3-tts-cpp nvidia: cuda12-qwen3-tts-cpp nvidia-cuda-12: cuda12-qwen3-tts-cpp nvidia-cuda-13: cuda13-qwen3-tts-cpp nvidia-l4t: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen3-tts-cpp vulkan: vulkan-qwen3-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-qwen3-tts-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-qwen3-tts-cpp - name: rocm-qwen3-tts-cpp-development alias: qwen3-tts-cpp description: | Qwen3-TTS C++ backend using GGML (qwentts.cpp). Native C++ text-to-speech with streaming output, named speakers, voice design, and zero-shot voice cloning. 24kHz mono, 11 languages with Mandarin dialects. 0.6B and 1.7B models in Q8_0 / Q4_K_M. urls: - https://github.com/ServeurpersoCom/qwentts.cpp tags: - text-to-speech - tts - voice-cloning - streaming capabilities: amd: rocm-qwen3-tts-cpp default: cpu-qwen3-tts-cpp intel: intel-sycl-f16-qwen3-tts-cpp metal: metal-qwen3-tts-cpp nvidia: cuda12-qwen3-tts-cpp nvidia-cuda-12: cuda12-qwen3-tts-cpp nvidia-cuda-13: cuda13-qwen3-tts-cpp nvidia-l4t: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen3-tts-cpp vulkan: vulkan-qwen3-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-qwen3-tts-cpp mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-qwen3-tts-cpp - name: intel-sycl-f32-qwen3-tts-cpp-development alias: qwen3-tts-cpp description: | Qwen3-TTS C++ backend using GGML (qwentts.cpp). Native C++ text-to-speech with streaming output, named speakers, voice design, and zero-shot voice cloning. 24kHz mono, 11 languages with Mandarin dialects. 0.6B and 1.7B models in Q8_0 / Q4_K_M. urls: - https://github.com/ServeurpersoCom/qwentts.cpp tags: - text-to-speech - tts - voice-cloning - streaming capabilities: amd: rocm-qwen3-tts-cpp default: cpu-qwen3-tts-cpp intel: intel-sycl-f16-qwen3-tts-cpp metal: metal-qwen3-tts-cpp nvidia: cuda12-qwen3-tts-cpp nvidia-cuda-12: cuda12-qwen3-tts-cpp nvidia-cuda-13: cuda13-qwen3-tts-cpp nvidia-l4t: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen3-tts-cpp vulkan: vulkan-qwen3-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-qwen3-tts-cpp mirrors: - localai/localai-backends:master-gpu-intel-sycl-f32-qwen3-tts-cpp - name: intel-sycl-f16-qwen3-tts-cpp-development alias: qwen3-tts-cpp description: | Qwen3-TTS C++ backend using GGML (qwentts.cpp). Native C++ text-to-speech with streaming output, named speakers, voice design, and zero-shot voice cloning. 24kHz mono, 11 languages with Mandarin dialects. 0.6B and 1.7B models in Q8_0 / Q4_K_M. urls: - https://github.com/ServeurpersoCom/qwentts.cpp tags: - text-to-speech - tts - voice-cloning - streaming capabilities: amd: rocm-qwen3-tts-cpp default: cpu-qwen3-tts-cpp intel: intel-sycl-f16-qwen3-tts-cpp metal: metal-qwen3-tts-cpp nvidia: cuda12-qwen3-tts-cpp nvidia-cuda-12: cuda12-qwen3-tts-cpp nvidia-cuda-13: cuda13-qwen3-tts-cpp nvidia-l4t: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen3-tts-cpp vulkan: vulkan-qwen3-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-qwen3-tts-cpp mirrors: - localai/localai-backends:master-gpu-intel-sycl-f16-qwen3-tts-cpp - name: cuda13-qwen3-tts-cpp alias: qwen3-tts-cpp description: | Qwen3-TTS C++ backend using GGML (qwentts.cpp). Native C++ text-to-speech with streaming output, named speakers, voice design, and zero-shot voice cloning. 24kHz mono, 11 languages with Mandarin dialects. 0.6B and 1.7B models in Q8_0 / Q4_K_M. urls: - https://github.com/ServeurpersoCom/qwentts.cpp tags: - text-to-speech - tts - voice-cloning - streaming capabilities: amd: rocm-qwen3-tts-cpp default: cpu-qwen3-tts-cpp intel: intel-sycl-f16-qwen3-tts-cpp metal: metal-qwen3-tts-cpp nvidia: cuda12-qwen3-tts-cpp nvidia-cuda-12: cuda12-qwen3-tts-cpp nvidia-cuda-13: cuda13-qwen3-tts-cpp nvidia-l4t: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen3-tts-cpp vulkan: vulkan-qwen3-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-qwen3-tts-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-qwen3-tts-cpp - name: cuda13-qwen3-tts-cpp-development alias: qwen3-tts-cpp description: | Qwen3-TTS C++ backend using GGML (qwentts.cpp). Native C++ text-to-speech with streaming output, named speakers, voice design, and zero-shot voice cloning. 24kHz mono, 11 languages with Mandarin dialects. 0.6B and 1.7B models in Q8_0 / Q4_K_M. urls: - https://github.com/ServeurpersoCom/qwentts.cpp tags: - text-to-speech - tts - voice-cloning - streaming capabilities: amd: rocm-qwen3-tts-cpp default: cpu-qwen3-tts-cpp intel: intel-sycl-f16-qwen3-tts-cpp metal: metal-qwen3-tts-cpp nvidia: cuda12-qwen3-tts-cpp nvidia-cuda-12: cuda12-qwen3-tts-cpp nvidia-cuda-13: cuda13-qwen3-tts-cpp nvidia-l4t: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-qwen3-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen3-tts-cpp vulkan: vulkan-qwen3-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-qwen3-tts-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-qwen3-tts-cpp - name: nvidia-l4t-arm64-moss-tts-cpp alias: moss-tts-cpp description: | MOSS-TTS C++ backend using GGML (moss-tts.cpp). Native C++ text-to-speech for the OpenMOSS MOSS-TTS-Local Transformer v1.5 model (a GPT-J local transformer + MOSS-Audio-Tokenizer-v2 neural codec), running from a self-contained GGUF with no Python at inference time. 48kHz stereo output with reference-audio voice cloning. urls: - https://github.com/mudler/moss-tts.cpp - https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF tags: - text-to-speech - tts - voice-cloning capabilities: amd: rocm-moss-tts-cpp default: cpu-moss-tts-cpp intel: intel-sycl-f16-moss-tts-cpp metal: metal-moss-tts-cpp nvidia: cuda12-moss-tts-cpp nvidia-cuda-12: cuda12-moss-tts-cpp nvidia-cuda-13: cuda13-moss-tts-cpp nvidia-l4t: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-tts-cpp vulkan: vulkan-moss-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-moss-tts-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-arm64-moss-tts-cpp - name: nvidia-l4t-arm64-moss-tts-cpp-development alias: moss-tts-cpp description: | MOSS-TTS C++ backend using GGML (moss-tts.cpp). Native C++ text-to-speech for the OpenMOSS MOSS-TTS-Local Transformer v1.5 model (a GPT-J local transformer + MOSS-Audio-Tokenizer-v2 neural codec), running from a self-contained GGUF with no Python at inference time. 48kHz stereo output with reference-audio voice cloning. urls: - https://github.com/mudler/moss-tts.cpp - https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF tags: - text-to-speech - tts - voice-cloning capabilities: amd: rocm-moss-tts-cpp default: cpu-moss-tts-cpp intel: intel-sycl-f16-moss-tts-cpp metal: metal-moss-tts-cpp nvidia: cuda12-moss-tts-cpp nvidia-cuda-12: cuda12-moss-tts-cpp nvidia-cuda-13: cuda13-moss-tts-cpp nvidia-l4t: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-tts-cpp vulkan: vulkan-moss-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-moss-tts-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-arm64-moss-tts-cpp - name: cuda13-nvidia-l4t-arm64-moss-tts-cpp alias: moss-tts-cpp description: | MOSS-TTS C++ backend using GGML (moss-tts.cpp). Native C++ text-to-speech for the OpenMOSS MOSS-TTS-Local Transformer v1.5 model (a GPT-J local transformer + MOSS-Audio-Tokenizer-v2 neural codec), running from a self-contained GGUF with no Python at inference time. 48kHz stereo output with reference-audio voice cloning. urls: - https://github.com/mudler/moss-tts.cpp - https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF tags: - text-to-speech - tts - voice-cloning capabilities: amd: rocm-moss-tts-cpp default: cpu-moss-tts-cpp intel: intel-sycl-f16-moss-tts-cpp metal: metal-moss-tts-cpp nvidia: cuda12-moss-tts-cpp nvidia-cuda-12: cuda12-moss-tts-cpp nvidia-cuda-13: cuda13-moss-tts-cpp nvidia-l4t: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-tts-cpp vulkan: vulkan-moss-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-moss-tts-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-moss-tts-cpp - name: cuda13-nvidia-l4t-arm64-moss-tts-cpp-development alias: moss-tts-cpp description: | MOSS-TTS C++ backend using GGML (moss-tts.cpp). Native C++ text-to-speech for the OpenMOSS MOSS-TTS-Local Transformer v1.5 model (a GPT-J local transformer + MOSS-Audio-Tokenizer-v2 neural codec), running from a self-contained GGUF with no Python at inference time. 48kHz stereo output with reference-audio voice cloning. urls: - https://github.com/mudler/moss-tts.cpp - https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF tags: - text-to-speech - tts - voice-cloning capabilities: amd: rocm-moss-tts-cpp default: cpu-moss-tts-cpp intel: intel-sycl-f16-moss-tts-cpp metal: metal-moss-tts-cpp nvidia: cuda12-moss-tts-cpp nvidia-cuda-12: cuda12-moss-tts-cpp nvidia-cuda-13: cuda13-moss-tts-cpp nvidia-l4t: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-tts-cpp vulkan: vulkan-moss-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-moss-tts-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-moss-tts-cpp - name: cpu-moss-tts-cpp alias: moss-tts-cpp description: | MOSS-TTS C++ backend using GGML (moss-tts.cpp). Native C++ text-to-speech for the OpenMOSS MOSS-TTS-Local Transformer v1.5 model (a GPT-J local transformer + MOSS-Audio-Tokenizer-v2 neural codec), running from a self-contained GGUF with no Python at inference time. 48kHz stereo output with reference-audio voice cloning. urls: - https://github.com/mudler/moss-tts.cpp - https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF tags: - text-to-speech - tts - voice-cloning capabilities: amd: rocm-moss-tts-cpp default: cpu-moss-tts-cpp intel: intel-sycl-f16-moss-tts-cpp metal: metal-moss-tts-cpp nvidia: cuda12-moss-tts-cpp nvidia-cuda-12: cuda12-moss-tts-cpp nvidia-cuda-13: cuda13-moss-tts-cpp nvidia-l4t: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-tts-cpp vulkan: vulkan-moss-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-cpu-moss-tts-cpp mirrors: - localai/localai-backends:latest-cpu-moss-tts-cpp - name: metal-moss-tts-cpp alias: moss-tts-cpp description: | MOSS-TTS C++ backend using GGML (moss-tts.cpp). Native C++ text-to-speech for the OpenMOSS MOSS-TTS-Local Transformer v1.5 model (a GPT-J local transformer + MOSS-Audio-Tokenizer-v2 neural codec), running from a self-contained GGUF with no Python at inference time. 48kHz stereo output with reference-audio voice cloning. urls: - https://github.com/mudler/moss-tts.cpp - https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF tags: - text-to-speech - tts - voice-cloning capabilities: amd: rocm-moss-tts-cpp default: cpu-moss-tts-cpp intel: intel-sycl-f16-moss-tts-cpp metal: metal-moss-tts-cpp nvidia: cuda12-moss-tts-cpp nvidia-cuda-12: cuda12-moss-tts-cpp nvidia-cuda-13: cuda13-moss-tts-cpp nvidia-l4t: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-tts-cpp vulkan: vulkan-moss-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-moss-tts-cpp mirrors: - localai/localai-backends:latest-metal-darwin-arm64-moss-tts-cpp - name: metal-moss-tts-cpp-development alias: moss-tts-cpp description: | MOSS-TTS C++ backend using GGML (moss-tts.cpp). Native C++ text-to-speech for the OpenMOSS MOSS-TTS-Local Transformer v1.5 model (a GPT-J local transformer + MOSS-Audio-Tokenizer-v2 neural codec), running from a self-contained GGUF with no Python at inference time. 48kHz stereo output with reference-audio voice cloning. urls: - https://github.com/mudler/moss-tts.cpp - https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF tags: - text-to-speech - tts - voice-cloning capabilities: amd: rocm-moss-tts-cpp default: cpu-moss-tts-cpp intel: intel-sycl-f16-moss-tts-cpp metal: metal-moss-tts-cpp nvidia: cuda12-moss-tts-cpp nvidia-cuda-12: cuda12-moss-tts-cpp nvidia-cuda-13: cuda13-moss-tts-cpp nvidia-l4t: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-tts-cpp vulkan: vulkan-moss-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-moss-tts-cpp mirrors: - localai/localai-backends:master-metal-darwin-arm64-moss-tts-cpp - name: cpu-moss-tts-cpp-development alias: moss-tts-cpp description: | MOSS-TTS C++ backend using GGML (moss-tts.cpp). Native C++ text-to-speech for the OpenMOSS MOSS-TTS-Local Transformer v1.5 model (a GPT-J local transformer + MOSS-Audio-Tokenizer-v2 neural codec), running from a self-contained GGUF with no Python at inference time. 48kHz stereo output with reference-audio voice cloning. urls: - https://github.com/mudler/moss-tts.cpp - https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF tags: - text-to-speech - tts - voice-cloning capabilities: amd: rocm-moss-tts-cpp default: cpu-moss-tts-cpp intel: intel-sycl-f16-moss-tts-cpp metal: metal-moss-tts-cpp nvidia: cuda12-moss-tts-cpp nvidia-cuda-12: cuda12-moss-tts-cpp nvidia-cuda-13: cuda13-moss-tts-cpp nvidia-l4t: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-tts-cpp vulkan: vulkan-moss-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-cpu-moss-tts-cpp mirrors: - localai/localai-backends:master-cpu-moss-tts-cpp - name: cuda12-moss-tts-cpp alias: moss-tts-cpp description: | MOSS-TTS C++ backend using GGML (moss-tts.cpp). Native C++ text-to-speech for the OpenMOSS MOSS-TTS-Local Transformer v1.5 model (a GPT-J local transformer + MOSS-Audio-Tokenizer-v2 neural codec), running from a self-contained GGUF with no Python at inference time. 48kHz stereo output with reference-audio voice cloning. urls: - https://github.com/mudler/moss-tts.cpp - https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF tags: - text-to-speech - tts - voice-cloning capabilities: amd: rocm-moss-tts-cpp default: cpu-moss-tts-cpp intel: intel-sycl-f16-moss-tts-cpp metal: metal-moss-tts-cpp nvidia: cuda12-moss-tts-cpp nvidia-cuda-12: cuda12-moss-tts-cpp nvidia-cuda-13: cuda13-moss-tts-cpp nvidia-l4t: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-tts-cpp vulkan: vulkan-moss-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-moss-tts-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-moss-tts-cpp - name: rocm-moss-tts-cpp alias: moss-tts-cpp description: | MOSS-TTS C++ backend using GGML (moss-tts.cpp). Native C++ text-to-speech for the OpenMOSS MOSS-TTS-Local Transformer v1.5 model (a GPT-J local transformer + MOSS-Audio-Tokenizer-v2 neural codec), running from a self-contained GGUF with no Python at inference time. 48kHz stereo output with reference-audio voice cloning. urls: - https://github.com/mudler/moss-tts.cpp - https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF tags: - text-to-speech - tts - voice-cloning capabilities: amd: rocm-moss-tts-cpp default: cpu-moss-tts-cpp intel: intel-sycl-f16-moss-tts-cpp metal: metal-moss-tts-cpp nvidia: cuda12-moss-tts-cpp nvidia-cuda-12: cuda12-moss-tts-cpp nvidia-cuda-13: cuda13-moss-tts-cpp nvidia-l4t: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-tts-cpp vulkan: vulkan-moss-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-moss-tts-cpp mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-moss-tts-cpp - name: intel-sycl-f32-moss-tts-cpp alias: moss-tts-cpp description: | MOSS-TTS C++ backend using GGML (moss-tts.cpp). Native C++ text-to-speech for the OpenMOSS MOSS-TTS-Local Transformer v1.5 model (a GPT-J local transformer + MOSS-Audio-Tokenizer-v2 neural codec), running from a self-contained GGUF with no Python at inference time. 48kHz stereo output with reference-audio voice cloning. urls: - https://github.com/mudler/moss-tts.cpp - https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF tags: - text-to-speech - tts - voice-cloning capabilities: amd: rocm-moss-tts-cpp default: cpu-moss-tts-cpp intel: intel-sycl-f16-moss-tts-cpp metal: metal-moss-tts-cpp nvidia: cuda12-moss-tts-cpp nvidia-cuda-12: cuda12-moss-tts-cpp nvidia-cuda-13: cuda13-moss-tts-cpp nvidia-l4t: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-tts-cpp vulkan: vulkan-moss-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-moss-tts-cpp mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f32-moss-tts-cpp - name: intel-sycl-f16-moss-tts-cpp alias: moss-tts-cpp description: | MOSS-TTS C++ backend using GGML (moss-tts.cpp). Native C++ text-to-speech for the OpenMOSS MOSS-TTS-Local Transformer v1.5 model (a GPT-J local transformer + MOSS-Audio-Tokenizer-v2 neural codec), running from a self-contained GGUF with no Python at inference time. 48kHz stereo output with reference-audio voice cloning. urls: - https://github.com/mudler/moss-tts.cpp - https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF tags: - text-to-speech - tts - voice-cloning capabilities: amd: rocm-moss-tts-cpp default: cpu-moss-tts-cpp intel: intel-sycl-f16-moss-tts-cpp metal: metal-moss-tts-cpp nvidia: cuda12-moss-tts-cpp nvidia-cuda-12: cuda12-moss-tts-cpp nvidia-cuda-13: cuda13-moss-tts-cpp nvidia-l4t: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-tts-cpp vulkan: vulkan-moss-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-moss-tts-cpp mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f16-moss-tts-cpp - name: vulkan-moss-tts-cpp alias: moss-tts-cpp description: | MOSS-TTS C++ backend using GGML (moss-tts.cpp). Native C++ text-to-speech for the OpenMOSS MOSS-TTS-Local Transformer v1.5 model (a GPT-J local transformer + MOSS-Audio-Tokenizer-v2 neural codec), running from a self-contained GGUF with no Python at inference time. 48kHz stereo output with reference-audio voice cloning. urls: - https://github.com/mudler/moss-tts.cpp - https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF tags: - text-to-speech - tts - voice-cloning capabilities: amd: rocm-moss-tts-cpp default: cpu-moss-tts-cpp intel: intel-sycl-f16-moss-tts-cpp metal: metal-moss-tts-cpp nvidia: cuda12-moss-tts-cpp nvidia-cuda-12: cuda12-moss-tts-cpp nvidia-cuda-13: cuda13-moss-tts-cpp nvidia-l4t: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-tts-cpp vulkan: vulkan-moss-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-moss-tts-cpp mirrors: - localai/localai-backends:latest-gpu-vulkan-moss-tts-cpp - name: vulkan-moss-tts-cpp-development alias: moss-tts-cpp description: | MOSS-TTS C++ backend using GGML (moss-tts.cpp). Native C++ text-to-speech for the OpenMOSS MOSS-TTS-Local Transformer v1.5 model (a GPT-J local transformer + MOSS-Audio-Tokenizer-v2 neural codec), running from a self-contained GGUF with no Python at inference time. 48kHz stereo output with reference-audio voice cloning. urls: - https://github.com/mudler/moss-tts.cpp - https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF tags: - text-to-speech - tts - voice-cloning capabilities: amd: rocm-moss-tts-cpp default: cpu-moss-tts-cpp intel: intel-sycl-f16-moss-tts-cpp metal: metal-moss-tts-cpp nvidia: cuda12-moss-tts-cpp nvidia-cuda-12: cuda12-moss-tts-cpp nvidia-cuda-13: cuda13-moss-tts-cpp nvidia-l4t: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-tts-cpp vulkan: vulkan-moss-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-moss-tts-cpp mirrors: - localai/localai-backends:master-gpu-vulkan-moss-tts-cpp - name: cuda12-moss-tts-cpp-development alias: moss-tts-cpp description: | MOSS-TTS C++ backend using GGML (moss-tts.cpp). Native C++ text-to-speech for the OpenMOSS MOSS-TTS-Local Transformer v1.5 model (a GPT-J local transformer + MOSS-Audio-Tokenizer-v2 neural codec), running from a self-contained GGUF with no Python at inference time. 48kHz stereo output with reference-audio voice cloning. urls: - https://github.com/mudler/moss-tts.cpp - https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF tags: - text-to-speech - tts - voice-cloning capabilities: amd: rocm-moss-tts-cpp default: cpu-moss-tts-cpp intel: intel-sycl-f16-moss-tts-cpp metal: metal-moss-tts-cpp nvidia: cuda12-moss-tts-cpp nvidia-cuda-12: cuda12-moss-tts-cpp nvidia-cuda-13: cuda13-moss-tts-cpp nvidia-l4t: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-tts-cpp vulkan: vulkan-moss-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-moss-tts-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-moss-tts-cpp - name: rocm-moss-tts-cpp-development alias: moss-tts-cpp description: | MOSS-TTS C++ backend using GGML (moss-tts.cpp). Native C++ text-to-speech for the OpenMOSS MOSS-TTS-Local Transformer v1.5 model (a GPT-J local transformer + MOSS-Audio-Tokenizer-v2 neural codec), running from a self-contained GGUF with no Python at inference time. 48kHz stereo output with reference-audio voice cloning. urls: - https://github.com/mudler/moss-tts.cpp - https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF tags: - text-to-speech - tts - voice-cloning capabilities: amd: rocm-moss-tts-cpp default: cpu-moss-tts-cpp intel: intel-sycl-f16-moss-tts-cpp metal: metal-moss-tts-cpp nvidia: cuda12-moss-tts-cpp nvidia-cuda-12: cuda12-moss-tts-cpp nvidia-cuda-13: cuda13-moss-tts-cpp nvidia-l4t: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-tts-cpp vulkan: vulkan-moss-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-moss-tts-cpp mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-moss-tts-cpp - name: intel-sycl-f32-moss-tts-cpp-development alias: moss-tts-cpp description: | MOSS-TTS C++ backend using GGML (moss-tts.cpp). Native C++ text-to-speech for the OpenMOSS MOSS-TTS-Local Transformer v1.5 model (a GPT-J local transformer + MOSS-Audio-Tokenizer-v2 neural codec), running from a self-contained GGUF with no Python at inference time. 48kHz stereo output with reference-audio voice cloning. urls: - https://github.com/mudler/moss-tts.cpp - https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF tags: - text-to-speech - tts - voice-cloning capabilities: amd: rocm-moss-tts-cpp default: cpu-moss-tts-cpp intel: intel-sycl-f16-moss-tts-cpp metal: metal-moss-tts-cpp nvidia: cuda12-moss-tts-cpp nvidia-cuda-12: cuda12-moss-tts-cpp nvidia-cuda-13: cuda13-moss-tts-cpp nvidia-l4t: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-tts-cpp vulkan: vulkan-moss-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-moss-tts-cpp mirrors: - localai/localai-backends:master-gpu-intel-sycl-f32-moss-tts-cpp - name: intel-sycl-f16-moss-tts-cpp-development alias: moss-tts-cpp description: | MOSS-TTS C++ backend using GGML (moss-tts.cpp). Native C++ text-to-speech for the OpenMOSS MOSS-TTS-Local Transformer v1.5 model (a GPT-J local transformer + MOSS-Audio-Tokenizer-v2 neural codec), running from a self-contained GGUF with no Python at inference time. 48kHz stereo output with reference-audio voice cloning. urls: - https://github.com/mudler/moss-tts.cpp - https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF tags: - text-to-speech - tts - voice-cloning capabilities: amd: rocm-moss-tts-cpp default: cpu-moss-tts-cpp intel: intel-sycl-f16-moss-tts-cpp metal: metal-moss-tts-cpp nvidia: cuda12-moss-tts-cpp nvidia-cuda-12: cuda12-moss-tts-cpp nvidia-cuda-13: cuda13-moss-tts-cpp nvidia-l4t: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-tts-cpp vulkan: vulkan-moss-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-moss-tts-cpp mirrors: - localai/localai-backends:master-gpu-intel-sycl-f16-moss-tts-cpp - name: cuda13-moss-tts-cpp alias: moss-tts-cpp description: | MOSS-TTS C++ backend using GGML (moss-tts.cpp). Native C++ text-to-speech for the OpenMOSS MOSS-TTS-Local Transformer v1.5 model (a GPT-J local transformer + MOSS-Audio-Tokenizer-v2 neural codec), running from a self-contained GGUF with no Python at inference time. 48kHz stereo output with reference-audio voice cloning. urls: - https://github.com/mudler/moss-tts.cpp - https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF tags: - text-to-speech - tts - voice-cloning capabilities: amd: rocm-moss-tts-cpp default: cpu-moss-tts-cpp intel: intel-sycl-f16-moss-tts-cpp metal: metal-moss-tts-cpp nvidia: cuda12-moss-tts-cpp nvidia-cuda-12: cuda12-moss-tts-cpp nvidia-cuda-13: cuda13-moss-tts-cpp nvidia-l4t: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-tts-cpp vulkan: vulkan-moss-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-moss-tts-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-moss-tts-cpp - name: cuda13-moss-tts-cpp-development alias: moss-tts-cpp description: | MOSS-TTS C++ backend using GGML (moss-tts.cpp). Native C++ text-to-speech for the OpenMOSS MOSS-TTS-Local Transformer v1.5 model (a GPT-J local transformer + MOSS-Audio-Tokenizer-v2 neural codec), running from a self-contained GGUF with no Python at inference time. 48kHz stereo output with reference-audio voice cloning. urls: - https://github.com/mudler/moss-tts.cpp - https://huggingface.co/mudler/MOSS-TTS-Local-Transformer-v1.5-GGUF tags: - text-to-speech - tts - voice-cloning capabilities: amd: rocm-moss-tts-cpp default: cpu-moss-tts-cpp intel: intel-sycl-f16-moss-tts-cpp metal: metal-moss-tts-cpp nvidia: cuda12-moss-tts-cpp nvidia-cuda-12: cuda12-moss-tts-cpp nvidia-cuda-13: cuda13-moss-tts-cpp nvidia-l4t: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-moss-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-moss-tts-cpp vulkan: vulkan-moss-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-moss-tts-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-moss-tts-cpp - name: nvidia-l4t-arm64-magpie-tts-cpp alias: magpie-tts-cpp description: | Magpie TTS C++ backend using GGML (magpie-tts.cpp). Native C++ text-to-speech for NVIDIA's Magpie TTS Multilingual 357M model (encoder + autoregressive decoder over NanoCodec tokens), running from a single self-contained GGUF (model, codec, tokenizer, G2P dictionaries) with no Python at inference time. 22.05kHz mono output, 5 baked voices (Aria, Jason, John, Leo, Sofia), 9+ languages. urls: - https://github.com/mudler/magpie-tts.cpp - https://huggingface.co/mudler/magpie-tts.cpp-gguf tags: - text-to-speech - tts capabilities: amd: rocm-magpie-tts-cpp default: cpu-magpie-tts-cpp intel: intel-sycl-f16-magpie-tts-cpp metal: metal-magpie-tts-cpp nvidia: cuda12-magpie-tts-cpp nvidia-cuda-12: cuda12-magpie-tts-cpp nvidia-cuda-13: cuda13-magpie-tts-cpp nvidia-l4t: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-magpie-tts-cpp vulkan: vulkan-magpie-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-magpie-tts-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-arm64-magpie-tts-cpp - name: nvidia-l4t-arm64-magpie-tts-cpp-development alias: magpie-tts-cpp description: | Magpie TTS C++ backend using GGML (magpie-tts.cpp). Native C++ text-to-speech for NVIDIA's Magpie TTS Multilingual 357M model (encoder + autoregressive decoder over NanoCodec tokens), running from a single self-contained GGUF (model, codec, tokenizer, G2P dictionaries) with no Python at inference time. 22.05kHz mono output, 5 baked voices (Aria, Jason, John, Leo, Sofia), 9+ languages. urls: - https://github.com/mudler/magpie-tts.cpp - https://huggingface.co/mudler/magpie-tts.cpp-gguf tags: - text-to-speech - tts capabilities: amd: rocm-magpie-tts-cpp default: cpu-magpie-tts-cpp intel: intel-sycl-f16-magpie-tts-cpp metal: metal-magpie-tts-cpp nvidia: cuda12-magpie-tts-cpp nvidia-cuda-12: cuda12-magpie-tts-cpp nvidia-cuda-13: cuda13-magpie-tts-cpp nvidia-l4t: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-magpie-tts-cpp vulkan: vulkan-magpie-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-magpie-tts-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-arm64-magpie-tts-cpp - name: cuda13-nvidia-l4t-arm64-magpie-tts-cpp alias: magpie-tts-cpp description: | Magpie TTS C++ backend using GGML (magpie-tts.cpp). Native C++ text-to-speech for NVIDIA's Magpie TTS Multilingual 357M model (encoder + autoregressive decoder over NanoCodec tokens), running from a single self-contained GGUF (model, codec, tokenizer, G2P dictionaries) with no Python at inference time. 22.05kHz mono output, 5 baked voices (Aria, Jason, John, Leo, Sofia), 9+ languages. urls: - https://github.com/mudler/magpie-tts.cpp - https://huggingface.co/mudler/magpie-tts.cpp-gguf tags: - text-to-speech - tts capabilities: amd: rocm-magpie-tts-cpp default: cpu-magpie-tts-cpp intel: intel-sycl-f16-magpie-tts-cpp metal: metal-magpie-tts-cpp nvidia: cuda12-magpie-tts-cpp nvidia-cuda-12: cuda12-magpie-tts-cpp nvidia-cuda-13: cuda13-magpie-tts-cpp nvidia-l4t: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-magpie-tts-cpp vulkan: vulkan-magpie-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-magpie-tts-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-magpie-tts-cpp - name: cuda13-nvidia-l4t-arm64-magpie-tts-cpp-development alias: magpie-tts-cpp description: | Magpie TTS C++ backend using GGML (magpie-tts.cpp). Native C++ text-to-speech for NVIDIA's Magpie TTS Multilingual 357M model (encoder + autoregressive decoder over NanoCodec tokens), running from a single self-contained GGUF (model, codec, tokenizer, G2P dictionaries) with no Python at inference time. 22.05kHz mono output, 5 baked voices (Aria, Jason, John, Leo, Sofia), 9+ languages. urls: - https://github.com/mudler/magpie-tts.cpp - https://huggingface.co/mudler/magpie-tts.cpp-gguf tags: - text-to-speech - tts capabilities: amd: rocm-magpie-tts-cpp default: cpu-magpie-tts-cpp intel: intel-sycl-f16-magpie-tts-cpp metal: metal-magpie-tts-cpp nvidia: cuda12-magpie-tts-cpp nvidia-cuda-12: cuda12-magpie-tts-cpp nvidia-cuda-13: cuda13-magpie-tts-cpp nvidia-l4t: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-magpie-tts-cpp vulkan: vulkan-magpie-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-magpie-tts-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-magpie-tts-cpp - name: cpu-magpie-tts-cpp alias: magpie-tts-cpp description: | Magpie TTS C++ backend using GGML (magpie-tts.cpp). Native C++ text-to-speech for NVIDIA's Magpie TTS Multilingual 357M model (encoder + autoregressive decoder over NanoCodec tokens), running from a single self-contained GGUF (model, codec, tokenizer, G2P dictionaries) with no Python at inference time. 22.05kHz mono output, 5 baked voices (Aria, Jason, John, Leo, Sofia), 9+ languages. urls: - https://github.com/mudler/magpie-tts.cpp - https://huggingface.co/mudler/magpie-tts.cpp-gguf tags: - text-to-speech - tts capabilities: amd: rocm-magpie-tts-cpp default: cpu-magpie-tts-cpp intel: intel-sycl-f16-magpie-tts-cpp metal: metal-magpie-tts-cpp nvidia: cuda12-magpie-tts-cpp nvidia-cuda-12: cuda12-magpie-tts-cpp nvidia-cuda-13: cuda13-magpie-tts-cpp nvidia-l4t: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-magpie-tts-cpp vulkan: vulkan-magpie-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-cpu-magpie-tts-cpp mirrors: - localai/localai-backends:latest-cpu-magpie-tts-cpp - name: metal-magpie-tts-cpp alias: magpie-tts-cpp description: | Magpie TTS C++ backend using GGML (magpie-tts.cpp). Native C++ text-to-speech for NVIDIA's Magpie TTS Multilingual 357M model (encoder + autoregressive decoder over NanoCodec tokens), running from a single self-contained GGUF (model, codec, tokenizer, G2P dictionaries) with no Python at inference time. 22.05kHz mono output, 5 baked voices (Aria, Jason, John, Leo, Sofia), 9+ languages. urls: - https://github.com/mudler/magpie-tts.cpp - https://huggingface.co/mudler/magpie-tts.cpp-gguf tags: - text-to-speech - tts capabilities: amd: rocm-magpie-tts-cpp default: cpu-magpie-tts-cpp intel: intel-sycl-f16-magpie-tts-cpp metal: metal-magpie-tts-cpp nvidia: cuda12-magpie-tts-cpp nvidia-cuda-12: cuda12-magpie-tts-cpp nvidia-cuda-13: cuda13-magpie-tts-cpp nvidia-l4t: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-magpie-tts-cpp vulkan: vulkan-magpie-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-magpie-tts-cpp mirrors: - localai/localai-backends:latest-metal-darwin-arm64-magpie-tts-cpp - name: metal-magpie-tts-cpp-development alias: magpie-tts-cpp description: | Magpie TTS C++ backend using GGML (magpie-tts.cpp). Native C++ text-to-speech for NVIDIA's Magpie TTS Multilingual 357M model (encoder + autoregressive decoder over NanoCodec tokens), running from a single self-contained GGUF (model, codec, tokenizer, G2P dictionaries) with no Python at inference time. 22.05kHz mono output, 5 baked voices (Aria, Jason, John, Leo, Sofia), 9+ languages. urls: - https://github.com/mudler/magpie-tts.cpp - https://huggingface.co/mudler/magpie-tts.cpp-gguf tags: - text-to-speech - tts capabilities: amd: rocm-magpie-tts-cpp default: cpu-magpie-tts-cpp intel: intel-sycl-f16-magpie-tts-cpp metal: metal-magpie-tts-cpp nvidia: cuda12-magpie-tts-cpp nvidia-cuda-12: cuda12-magpie-tts-cpp nvidia-cuda-13: cuda13-magpie-tts-cpp nvidia-l4t: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-magpie-tts-cpp vulkan: vulkan-magpie-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-magpie-tts-cpp mirrors: - localai/localai-backends:master-metal-darwin-arm64-magpie-tts-cpp - name: cpu-magpie-tts-cpp-development alias: magpie-tts-cpp description: | Magpie TTS C++ backend using GGML (magpie-tts.cpp). Native C++ text-to-speech for NVIDIA's Magpie TTS Multilingual 357M model (encoder + autoregressive decoder over NanoCodec tokens), running from a single self-contained GGUF (model, codec, tokenizer, G2P dictionaries) with no Python at inference time. 22.05kHz mono output, 5 baked voices (Aria, Jason, John, Leo, Sofia), 9+ languages. urls: - https://github.com/mudler/magpie-tts.cpp - https://huggingface.co/mudler/magpie-tts.cpp-gguf tags: - text-to-speech - tts capabilities: amd: rocm-magpie-tts-cpp default: cpu-magpie-tts-cpp intel: intel-sycl-f16-magpie-tts-cpp metal: metal-magpie-tts-cpp nvidia: cuda12-magpie-tts-cpp nvidia-cuda-12: cuda12-magpie-tts-cpp nvidia-cuda-13: cuda13-magpie-tts-cpp nvidia-l4t: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-magpie-tts-cpp vulkan: vulkan-magpie-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-cpu-magpie-tts-cpp mirrors: - localai/localai-backends:master-cpu-magpie-tts-cpp - name: cuda12-magpie-tts-cpp alias: magpie-tts-cpp description: | Magpie TTS C++ backend using GGML (magpie-tts.cpp). Native C++ text-to-speech for NVIDIA's Magpie TTS Multilingual 357M model (encoder + autoregressive decoder over NanoCodec tokens), running from a single self-contained GGUF (model, codec, tokenizer, G2P dictionaries) with no Python at inference time. 22.05kHz mono output, 5 baked voices (Aria, Jason, John, Leo, Sofia), 9+ languages. urls: - https://github.com/mudler/magpie-tts.cpp - https://huggingface.co/mudler/magpie-tts.cpp-gguf tags: - text-to-speech - tts capabilities: amd: rocm-magpie-tts-cpp default: cpu-magpie-tts-cpp intel: intel-sycl-f16-magpie-tts-cpp metal: metal-magpie-tts-cpp nvidia: cuda12-magpie-tts-cpp nvidia-cuda-12: cuda12-magpie-tts-cpp nvidia-cuda-13: cuda13-magpie-tts-cpp nvidia-l4t: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-magpie-tts-cpp vulkan: vulkan-magpie-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-magpie-tts-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-magpie-tts-cpp - name: rocm-magpie-tts-cpp alias: magpie-tts-cpp description: | Magpie TTS C++ backend using GGML (magpie-tts.cpp). Native C++ text-to-speech for NVIDIA's Magpie TTS Multilingual 357M model (encoder + autoregressive decoder over NanoCodec tokens), running from a single self-contained GGUF (model, codec, tokenizer, G2P dictionaries) with no Python at inference time. 22.05kHz mono output, 5 baked voices (Aria, Jason, John, Leo, Sofia), 9+ languages. urls: - https://github.com/mudler/magpie-tts.cpp - https://huggingface.co/mudler/magpie-tts.cpp-gguf tags: - text-to-speech - tts capabilities: amd: rocm-magpie-tts-cpp default: cpu-magpie-tts-cpp intel: intel-sycl-f16-magpie-tts-cpp metal: metal-magpie-tts-cpp nvidia: cuda12-magpie-tts-cpp nvidia-cuda-12: cuda12-magpie-tts-cpp nvidia-cuda-13: cuda13-magpie-tts-cpp nvidia-l4t: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-magpie-tts-cpp vulkan: vulkan-magpie-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-magpie-tts-cpp mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-magpie-tts-cpp - name: intel-sycl-f32-magpie-tts-cpp alias: magpie-tts-cpp description: | Magpie TTS C++ backend using GGML (magpie-tts.cpp). Native C++ text-to-speech for NVIDIA's Magpie TTS Multilingual 357M model (encoder + autoregressive decoder over NanoCodec tokens), running from a single self-contained GGUF (model, codec, tokenizer, G2P dictionaries) with no Python at inference time. 22.05kHz mono output, 5 baked voices (Aria, Jason, John, Leo, Sofia), 9+ languages. urls: - https://github.com/mudler/magpie-tts.cpp - https://huggingface.co/mudler/magpie-tts.cpp-gguf tags: - text-to-speech - tts capabilities: amd: rocm-magpie-tts-cpp default: cpu-magpie-tts-cpp intel: intel-sycl-f16-magpie-tts-cpp metal: metal-magpie-tts-cpp nvidia: cuda12-magpie-tts-cpp nvidia-cuda-12: cuda12-magpie-tts-cpp nvidia-cuda-13: cuda13-magpie-tts-cpp nvidia-l4t: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-magpie-tts-cpp vulkan: vulkan-magpie-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-magpie-tts-cpp mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f32-magpie-tts-cpp - name: intel-sycl-f16-magpie-tts-cpp alias: magpie-tts-cpp description: | Magpie TTS C++ backend using GGML (magpie-tts.cpp). Native C++ text-to-speech for NVIDIA's Magpie TTS Multilingual 357M model (encoder + autoregressive decoder over NanoCodec tokens), running from a single self-contained GGUF (model, codec, tokenizer, G2P dictionaries) with no Python at inference time. 22.05kHz mono output, 5 baked voices (Aria, Jason, John, Leo, Sofia), 9+ languages. urls: - https://github.com/mudler/magpie-tts.cpp - https://huggingface.co/mudler/magpie-tts.cpp-gguf tags: - text-to-speech - tts capabilities: amd: rocm-magpie-tts-cpp default: cpu-magpie-tts-cpp intel: intel-sycl-f16-magpie-tts-cpp metal: metal-magpie-tts-cpp nvidia: cuda12-magpie-tts-cpp nvidia-cuda-12: cuda12-magpie-tts-cpp nvidia-cuda-13: cuda13-magpie-tts-cpp nvidia-l4t: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-magpie-tts-cpp vulkan: vulkan-magpie-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-magpie-tts-cpp mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f16-magpie-tts-cpp - name: vulkan-magpie-tts-cpp alias: magpie-tts-cpp description: | Magpie TTS C++ backend using GGML (magpie-tts.cpp). Native C++ text-to-speech for NVIDIA's Magpie TTS Multilingual 357M model (encoder + autoregressive decoder over NanoCodec tokens), running from a single self-contained GGUF (model, codec, tokenizer, G2P dictionaries) with no Python at inference time. 22.05kHz mono output, 5 baked voices (Aria, Jason, John, Leo, Sofia), 9+ languages. urls: - https://github.com/mudler/magpie-tts.cpp - https://huggingface.co/mudler/magpie-tts.cpp-gguf tags: - text-to-speech - tts capabilities: amd: rocm-magpie-tts-cpp default: cpu-magpie-tts-cpp intel: intel-sycl-f16-magpie-tts-cpp metal: metal-magpie-tts-cpp nvidia: cuda12-magpie-tts-cpp nvidia-cuda-12: cuda12-magpie-tts-cpp nvidia-cuda-13: cuda13-magpie-tts-cpp nvidia-l4t: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-magpie-tts-cpp vulkan: vulkan-magpie-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-magpie-tts-cpp mirrors: - localai/localai-backends:latest-gpu-vulkan-magpie-tts-cpp - name: vulkan-magpie-tts-cpp-development alias: magpie-tts-cpp description: | Magpie TTS C++ backend using GGML (magpie-tts.cpp). Native C++ text-to-speech for NVIDIA's Magpie TTS Multilingual 357M model (encoder + autoregressive decoder over NanoCodec tokens), running from a single self-contained GGUF (model, codec, tokenizer, G2P dictionaries) with no Python at inference time. 22.05kHz mono output, 5 baked voices (Aria, Jason, John, Leo, Sofia), 9+ languages. urls: - https://github.com/mudler/magpie-tts.cpp - https://huggingface.co/mudler/magpie-tts.cpp-gguf tags: - text-to-speech - tts capabilities: amd: rocm-magpie-tts-cpp default: cpu-magpie-tts-cpp intel: intel-sycl-f16-magpie-tts-cpp metal: metal-magpie-tts-cpp nvidia: cuda12-magpie-tts-cpp nvidia-cuda-12: cuda12-magpie-tts-cpp nvidia-cuda-13: cuda13-magpie-tts-cpp nvidia-l4t: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-magpie-tts-cpp vulkan: vulkan-magpie-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-magpie-tts-cpp mirrors: - localai/localai-backends:master-gpu-vulkan-magpie-tts-cpp - name: cuda12-magpie-tts-cpp-development alias: magpie-tts-cpp description: | Magpie TTS C++ backend using GGML (magpie-tts.cpp). Native C++ text-to-speech for NVIDIA's Magpie TTS Multilingual 357M model (encoder + autoregressive decoder over NanoCodec tokens), running from a single self-contained GGUF (model, codec, tokenizer, G2P dictionaries) with no Python at inference time. 22.05kHz mono output, 5 baked voices (Aria, Jason, John, Leo, Sofia), 9+ languages. urls: - https://github.com/mudler/magpie-tts.cpp - https://huggingface.co/mudler/magpie-tts.cpp-gguf tags: - text-to-speech - tts capabilities: amd: rocm-magpie-tts-cpp default: cpu-magpie-tts-cpp intel: intel-sycl-f16-magpie-tts-cpp metal: metal-magpie-tts-cpp nvidia: cuda12-magpie-tts-cpp nvidia-cuda-12: cuda12-magpie-tts-cpp nvidia-cuda-13: cuda13-magpie-tts-cpp nvidia-l4t: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-magpie-tts-cpp vulkan: vulkan-magpie-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-magpie-tts-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-magpie-tts-cpp - name: rocm-magpie-tts-cpp-development alias: magpie-tts-cpp description: | Magpie TTS C++ backend using GGML (magpie-tts.cpp). Native C++ text-to-speech for NVIDIA's Magpie TTS Multilingual 357M model (encoder + autoregressive decoder over NanoCodec tokens), running from a single self-contained GGUF (model, codec, tokenizer, G2P dictionaries) with no Python at inference time. 22.05kHz mono output, 5 baked voices (Aria, Jason, John, Leo, Sofia), 9+ languages. urls: - https://github.com/mudler/magpie-tts.cpp - https://huggingface.co/mudler/magpie-tts.cpp-gguf tags: - text-to-speech - tts capabilities: amd: rocm-magpie-tts-cpp default: cpu-magpie-tts-cpp intel: intel-sycl-f16-magpie-tts-cpp metal: metal-magpie-tts-cpp nvidia: cuda12-magpie-tts-cpp nvidia-cuda-12: cuda12-magpie-tts-cpp nvidia-cuda-13: cuda13-magpie-tts-cpp nvidia-l4t: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-magpie-tts-cpp vulkan: vulkan-magpie-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-magpie-tts-cpp mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-magpie-tts-cpp - name: intel-sycl-f32-magpie-tts-cpp-development alias: magpie-tts-cpp description: | Magpie TTS C++ backend using GGML (magpie-tts.cpp). Native C++ text-to-speech for NVIDIA's Magpie TTS Multilingual 357M model (encoder + autoregressive decoder over NanoCodec tokens), running from a single self-contained GGUF (model, codec, tokenizer, G2P dictionaries) with no Python at inference time. 22.05kHz mono output, 5 baked voices (Aria, Jason, John, Leo, Sofia), 9+ languages. urls: - https://github.com/mudler/magpie-tts.cpp - https://huggingface.co/mudler/magpie-tts.cpp-gguf tags: - text-to-speech - tts capabilities: amd: rocm-magpie-tts-cpp default: cpu-magpie-tts-cpp intel: intel-sycl-f16-magpie-tts-cpp metal: metal-magpie-tts-cpp nvidia: cuda12-magpie-tts-cpp nvidia-cuda-12: cuda12-magpie-tts-cpp nvidia-cuda-13: cuda13-magpie-tts-cpp nvidia-l4t: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-magpie-tts-cpp vulkan: vulkan-magpie-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-magpie-tts-cpp mirrors: - localai/localai-backends:master-gpu-intel-sycl-f32-magpie-tts-cpp - name: intel-sycl-f16-magpie-tts-cpp-development alias: magpie-tts-cpp description: | Magpie TTS C++ backend using GGML (magpie-tts.cpp). Native C++ text-to-speech for NVIDIA's Magpie TTS Multilingual 357M model (encoder + autoregressive decoder over NanoCodec tokens), running from a single self-contained GGUF (model, codec, tokenizer, G2P dictionaries) with no Python at inference time. 22.05kHz mono output, 5 baked voices (Aria, Jason, John, Leo, Sofia), 9+ languages. urls: - https://github.com/mudler/magpie-tts.cpp - https://huggingface.co/mudler/magpie-tts.cpp-gguf tags: - text-to-speech - tts capabilities: amd: rocm-magpie-tts-cpp default: cpu-magpie-tts-cpp intel: intel-sycl-f16-magpie-tts-cpp metal: metal-magpie-tts-cpp nvidia: cuda12-magpie-tts-cpp nvidia-cuda-12: cuda12-magpie-tts-cpp nvidia-cuda-13: cuda13-magpie-tts-cpp nvidia-l4t: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-magpie-tts-cpp vulkan: vulkan-magpie-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-magpie-tts-cpp mirrors: - localai/localai-backends:master-gpu-intel-sycl-f16-magpie-tts-cpp - name: cuda13-magpie-tts-cpp alias: magpie-tts-cpp description: | Magpie TTS C++ backend using GGML (magpie-tts.cpp). Native C++ text-to-speech for NVIDIA's Magpie TTS Multilingual 357M model (encoder + autoregressive decoder over NanoCodec tokens), running from a single self-contained GGUF (model, codec, tokenizer, G2P dictionaries) with no Python at inference time. 22.05kHz mono output, 5 baked voices (Aria, Jason, John, Leo, Sofia), 9+ languages. urls: - https://github.com/mudler/magpie-tts.cpp - https://huggingface.co/mudler/magpie-tts.cpp-gguf tags: - text-to-speech - tts capabilities: amd: rocm-magpie-tts-cpp default: cpu-magpie-tts-cpp intel: intel-sycl-f16-magpie-tts-cpp metal: metal-magpie-tts-cpp nvidia: cuda12-magpie-tts-cpp nvidia-cuda-12: cuda12-magpie-tts-cpp nvidia-cuda-13: cuda13-magpie-tts-cpp nvidia-l4t: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-magpie-tts-cpp vulkan: vulkan-magpie-tts-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-magpie-tts-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-magpie-tts-cpp - name: cuda13-magpie-tts-cpp-development alias: magpie-tts-cpp description: | Magpie TTS C++ backend using GGML (magpie-tts.cpp). Native C++ text-to-speech for NVIDIA's Magpie TTS Multilingual 357M model (encoder + autoregressive decoder over NanoCodec tokens), running from a single self-contained GGUF (model, codec, tokenizer, G2P dictionaries) with no Python at inference time. 22.05kHz mono output, 5 baked voices (Aria, Jason, John, Leo, Sofia), 9+ languages. urls: - https://github.com/mudler/magpie-tts.cpp - https://huggingface.co/mudler/magpie-tts.cpp-gguf tags: - text-to-speech - tts capabilities: amd: rocm-magpie-tts-cpp default: cpu-magpie-tts-cpp intel: intel-sycl-f16-magpie-tts-cpp metal: metal-magpie-tts-cpp nvidia: cuda12-magpie-tts-cpp nvidia-cuda-12: cuda12-magpie-tts-cpp nvidia-cuda-13: cuda13-magpie-tts-cpp nvidia-l4t: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-magpie-tts-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-magpie-tts-cpp vulkan: vulkan-magpie-tts-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-magpie-tts-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-magpie-tts-cpp - name: omnivoice-cpp-development alias: omnivoice-cpp description: | OmniVoice C++ backend using GGML. Native text-to-speech with voice cloning (reference audio + transcript) and voice design (attribute keywords: gender, age, pitch, style, volume, emotion). 24kHz mono output, 646 languages. Supports streaming synthesis. urls: - https://github.com/ServeurpersoCom/omnivoice.cpp tags: - text-to-speech - tts - voice-cloning - voice-design capabilities: amd: rocm-omnivoice-cpp-development default: cpu-omnivoice-cpp-development intel: intel-sycl-f16-omnivoice-cpp-development metal: metal-omnivoice-cpp-development nvidia: cuda12-omnivoice-cpp-development nvidia-cuda-12: cuda12-omnivoice-cpp-development nvidia-cuda-13: cuda13-omnivoice-cpp-development nvidia-l4t: nvidia-l4t-arm64-omnivoice-cpp-development nvidia-l4t-cuda-12: nvidia-l4t-arm64-omnivoice-cpp-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-omnivoice-cpp-development vulkan: vulkan-omnivoice-cpp-development - name: nvidia-l4t-arm64-omnivoice-cpp alias: omnivoice-cpp description: | OmniVoice C++ backend using GGML. Native text-to-speech with voice cloning (reference audio + transcript) and voice design (attribute keywords: gender, age, pitch, style, volume, emotion). 24kHz mono output, 646 languages. Supports streaming synthesis. urls: - https://github.com/ServeurpersoCom/omnivoice.cpp tags: - text-to-speech - tts - voice-cloning - voice-design capabilities: amd: rocm-omnivoice-cpp default: cpu-omnivoice-cpp intel: intel-sycl-f16-omnivoice-cpp metal: metal-omnivoice-cpp nvidia: cuda12-omnivoice-cpp nvidia-cuda-12: cuda12-omnivoice-cpp nvidia-cuda-13: cuda13-omnivoice-cpp nvidia-l4t: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-omnivoice-cpp vulkan: vulkan-omnivoice-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-omnivoice-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-arm64-omnivoice-cpp - name: nvidia-l4t-arm64-omnivoice-cpp-development alias: omnivoice-cpp description: | OmniVoice C++ backend using GGML. Native text-to-speech with voice cloning (reference audio + transcript) and voice design (attribute keywords: gender, age, pitch, style, volume, emotion). 24kHz mono output, 646 languages. Supports streaming synthesis. urls: - https://github.com/ServeurpersoCom/omnivoice.cpp tags: - text-to-speech - tts - voice-cloning - voice-design capabilities: amd: rocm-omnivoice-cpp default: cpu-omnivoice-cpp intel: intel-sycl-f16-omnivoice-cpp metal: metal-omnivoice-cpp nvidia: cuda12-omnivoice-cpp nvidia-cuda-12: cuda12-omnivoice-cpp nvidia-cuda-13: cuda13-omnivoice-cpp nvidia-l4t: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-omnivoice-cpp vulkan: vulkan-omnivoice-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-omnivoice-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-arm64-omnivoice-cpp - name: cuda13-nvidia-l4t-arm64-omnivoice-cpp alias: omnivoice-cpp description: | OmniVoice C++ backend using GGML. Native text-to-speech with voice cloning (reference audio + transcript) and voice design (attribute keywords: gender, age, pitch, style, volume, emotion). 24kHz mono output, 646 languages. Supports streaming synthesis. urls: - https://github.com/ServeurpersoCom/omnivoice.cpp tags: - text-to-speech - tts - voice-cloning - voice-design capabilities: amd: rocm-omnivoice-cpp default: cpu-omnivoice-cpp intel: intel-sycl-f16-omnivoice-cpp metal: metal-omnivoice-cpp nvidia: cuda12-omnivoice-cpp nvidia-cuda-12: cuda12-omnivoice-cpp nvidia-cuda-13: cuda13-omnivoice-cpp nvidia-l4t: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-omnivoice-cpp vulkan: vulkan-omnivoice-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-omnivoice-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-omnivoice-cpp - name: cuda13-nvidia-l4t-arm64-omnivoice-cpp-development alias: omnivoice-cpp description: | OmniVoice C++ backend using GGML. Native text-to-speech with voice cloning (reference audio + transcript) and voice design (attribute keywords: gender, age, pitch, style, volume, emotion). 24kHz mono output, 646 languages. Supports streaming synthesis. urls: - https://github.com/ServeurpersoCom/omnivoice.cpp tags: - text-to-speech - tts - voice-cloning - voice-design capabilities: amd: rocm-omnivoice-cpp default: cpu-omnivoice-cpp intel: intel-sycl-f16-omnivoice-cpp metal: metal-omnivoice-cpp nvidia: cuda12-omnivoice-cpp nvidia-cuda-12: cuda12-omnivoice-cpp nvidia-cuda-13: cuda13-omnivoice-cpp nvidia-l4t: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-omnivoice-cpp vulkan: vulkan-omnivoice-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-omnivoice-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-omnivoice-cpp - name: cpu-omnivoice-cpp alias: omnivoice-cpp description: | OmniVoice C++ backend using GGML. Native text-to-speech with voice cloning (reference audio + transcript) and voice design (attribute keywords: gender, age, pitch, style, volume, emotion). 24kHz mono output, 646 languages. Supports streaming synthesis. urls: - https://github.com/ServeurpersoCom/omnivoice.cpp tags: - text-to-speech - tts - voice-cloning - voice-design capabilities: amd: rocm-omnivoice-cpp default: cpu-omnivoice-cpp intel: intel-sycl-f16-omnivoice-cpp metal: metal-omnivoice-cpp nvidia: cuda12-omnivoice-cpp nvidia-cuda-12: cuda12-omnivoice-cpp nvidia-cuda-13: cuda13-omnivoice-cpp nvidia-l4t: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-omnivoice-cpp vulkan: vulkan-omnivoice-cpp uri: quay.io/go-skynet/local-ai-backends:latest-cpu-omnivoice-cpp mirrors: - localai/localai-backends:latest-cpu-omnivoice-cpp - name: metal-omnivoice-cpp alias: omnivoice-cpp description: | OmniVoice C++ backend using GGML. Native text-to-speech with voice cloning (reference audio + transcript) and voice design (attribute keywords: gender, age, pitch, style, volume, emotion). 24kHz mono output, 646 languages. Supports streaming synthesis. urls: - https://github.com/ServeurpersoCom/omnivoice.cpp tags: - text-to-speech - tts - voice-cloning - voice-design capabilities: amd: rocm-omnivoice-cpp default: cpu-omnivoice-cpp intel: intel-sycl-f16-omnivoice-cpp metal: metal-omnivoice-cpp nvidia: cuda12-omnivoice-cpp nvidia-cuda-12: cuda12-omnivoice-cpp nvidia-cuda-13: cuda13-omnivoice-cpp nvidia-l4t: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-omnivoice-cpp vulkan: vulkan-omnivoice-cpp uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-omnivoice-cpp mirrors: - localai/localai-backends:latest-metal-darwin-arm64-omnivoice-cpp - name: metal-omnivoice-cpp-development alias: omnivoice-cpp description: | OmniVoice C++ backend using GGML. Native text-to-speech with voice cloning (reference audio + transcript) and voice design (attribute keywords: gender, age, pitch, style, volume, emotion). 24kHz mono output, 646 languages. Supports streaming synthesis. urls: - https://github.com/ServeurpersoCom/omnivoice.cpp tags: - text-to-speech - tts - voice-cloning - voice-design capabilities: amd: rocm-omnivoice-cpp default: cpu-omnivoice-cpp intel: intel-sycl-f16-omnivoice-cpp metal: metal-omnivoice-cpp nvidia: cuda12-omnivoice-cpp nvidia-cuda-12: cuda12-omnivoice-cpp nvidia-cuda-13: cuda13-omnivoice-cpp nvidia-l4t: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-omnivoice-cpp vulkan: vulkan-omnivoice-cpp uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-omnivoice-cpp mirrors: - localai/localai-backends:master-metal-darwin-arm64-omnivoice-cpp - name: cpu-omnivoice-cpp-development alias: omnivoice-cpp description: | OmniVoice C++ backend using GGML. Native text-to-speech with voice cloning (reference audio + transcript) and voice design (attribute keywords: gender, age, pitch, style, volume, emotion). 24kHz mono output, 646 languages. Supports streaming synthesis. urls: - https://github.com/ServeurpersoCom/omnivoice.cpp tags: - text-to-speech - tts - voice-cloning - voice-design capabilities: amd: rocm-omnivoice-cpp default: cpu-omnivoice-cpp intel: intel-sycl-f16-omnivoice-cpp metal: metal-omnivoice-cpp nvidia: cuda12-omnivoice-cpp nvidia-cuda-12: cuda12-omnivoice-cpp nvidia-cuda-13: cuda13-omnivoice-cpp nvidia-l4t: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-omnivoice-cpp vulkan: vulkan-omnivoice-cpp uri: quay.io/go-skynet/local-ai-backends:master-cpu-omnivoice-cpp mirrors: - localai/localai-backends:master-cpu-omnivoice-cpp - name: cuda12-omnivoice-cpp alias: omnivoice-cpp description: | OmniVoice C++ backend using GGML. Native text-to-speech with voice cloning (reference audio + transcript) and voice design (attribute keywords: gender, age, pitch, style, volume, emotion). 24kHz mono output, 646 languages. Supports streaming synthesis. urls: - https://github.com/ServeurpersoCom/omnivoice.cpp tags: - text-to-speech - tts - voice-cloning - voice-design capabilities: amd: rocm-omnivoice-cpp default: cpu-omnivoice-cpp intel: intel-sycl-f16-omnivoice-cpp metal: metal-omnivoice-cpp nvidia: cuda12-omnivoice-cpp nvidia-cuda-12: cuda12-omnivoice-cpp nvidia-cuda-13: cuda13-omnivoice-cpp nvidia-l4t: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-omnivoice-cpp vulkan: vulkan-omnivoice-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-omnivoice-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-omnivoice-cpp - name: rocm-omnivoice-cpp alias: omnivoice-cpp description: | OmniVoice C++ backend using GGML. Native text-to-speech with voice cloning (reference audio + transcript) and voice design (attribute keywords: gender, age, pitch, style, volume, emotion). 24kHz mono output, 646 languages. Supports streaming synthesis. urls: - https://github.com/ServeurpersoCom/omnivoice.cpp tags: - text-to-speech - tts - voice-cloning - voice-design capabilities: amd: rocm-omnivoice-cpp default: cpu-omnivoice-cpp intel: intel-sycl-f16-omnivoice-cpp metal: metal-omnivoice-cpp nvidia: cuda12-omnivoice-cpp nvidia-cuda-12: cuda12-omnivoice-cpp nvidia-cuda-13: cuda13-omnivoice-cpp nvidia-l4t: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-omnivoice-cpp vulkan: vulkan-omnivoice-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-omnivoice-cpp mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-omnivoice-cpp - name: intel-sycl-f32-omnivoice-cpp alias: omnivoice-cpp description: | OmniVoice C++ backend using GGML. Native text-to-speech with voice cloning (reference audio + transcript) and voice design (attribute keywords: gender, age, pitch, style, volume, emotion). 24kHz mono output, 646 languages. Supports streaming synthesis. urls: - https://github.com/ServeurpersoCom/omnivoice.cpp tags: - text-to-speech - tts - voice-cloning - voice-design capabilities: amd: rocm-omnivoice-cpp default: cpu-omnivoice-cpp intel: intel-sycl-f16-omnivoice-cpp metal: metal-omnivoice-cpp nvidia: cuda12-omnivoice-cpp nvidia-cuda-12: cuda12-omnivoice-cpp nvidia-cuda-13: cuda13-omnivoice-cpp nvidia-l4t: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-omnivoice-cpp vulkan: vulkan-omnivoice-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-omnivoice-cpp mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f32-omnivoice-cpp - name: intel-sycl-f16-omnivoice-cpp alias: omnivoice-cpp description: | OmniVoice C++ backend using GGML. Native text-to-speech with voice cloning (reference audio + transcript) and voice design (attribute keywords: gender, age, pitch, style, volume, emotion). 24kHz mono output, 646 languages. Supports streaming synthesis. urls: - https://github.com/ServeurpersoCom/omnivoice.cpp tags: - text-to-speech - tts - voice-cloning - voice-design capabilities: amd: rocm-omnivoice-cpp default: cpu-omnivoice-cpp intel: intel-sycl-f16-omnivoice-cpp metal: metal-omnivoice-cpp nvidia: cuda12-omnivoice-cpp nvidia-cuda-12: cuda12-omnivoice-cpp nvidia-cuda-13: cuda13-omnivoice-cpp nvidia-l4t: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-omnivoice-cpp vulkan: vulkan-omnivoice-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-omnivoice-cpp mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f16-omnivoice-cpp - name: vulkan-omnivoice-cpp alias: omnivoice-cpp description: | OmniVoice C++ backend using GGML. Native text-to-speech with voice cloning (reference audio + transcript) and voice design (attribute keywords: gender, age, pitch, style, volume, emotion). 24kHz mono output, 646 languages. Supports streaming synthesis. urls: - https://github.com/ServeurpersoCom/omnivoice.cpp tags: - text-to-speech - tts - voice-cloning - voice-design capabilities: amd: rocm-omnivoice-cpp default: cpu-omnivoice-cpp intel: intel-sycl-f16-omnivoice-cpp metal: metal-omnivoice-cpp nvidia: cuda12-omnivoice-cpp nvidia-cuda-12: cuda12-omnivoice-cpp nvidia-cuda-13: cuda13-omnivoice-cpp nvidia-l4t: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-omnivoice-cpp vulkan: vulkan-omnivoice-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-omnivoice-cpp mirrors: - localai/localai-backends:latest-gpu-vulkan-omnivoice-cpp - name: vulkan-omnivoice-cpp-development alias: omnivoice-cpp description: | OmniVoice C++ backend using GGML. Native text-to-speech with voice cloning (reference audio + transcript) and voice design (attribute keywords: gender, age, pitch, style, volume, emotion). 24kHz mono output, 646 languages. Supports streaming synthesis. urls: - https://github.com/ServeurpersoCom/omnivoice.cpp tags: - text-to-speech - tts - voice-cloning - voice-design capabilities: amd: rocm-omnivoice-cpp default: cpu-omnivoice-cpp intel: intel-sycl-f16-omnivoice-cpp metal: metal-omnivoice-cpp nvidia: cuda12-omnivoice-cpp nvidia-cuda-12: cuda12-omnivoice-cpp nvidia-cuda-13: cuda13-omnivoice-cpp nvidia-l4t: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-omnivoice-cpp vulkan: vulkan-omnivoice-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-omnivoice-cpp mirrors: - localai/localai-backends:master-gpu-vulkan-omnivoice-cpp - name: cuda12-omnivoice-cpp-development alias: omnivoice-cpp description: | OmniVoice C++ backend using GGML. Native text-to-speech with voice cloning (reference audio + transcript) and voice design (attribute keywords: gender, age, pitch, style, volume, emotion). 24kHz mono output, 646 languages. Supports streaming synthesis. urls: - https://github.com/ServeurpersoCom/omnivoice.cpp tags: - text-to-speech - tts - voice-cloning - voice-design capabilities: amd: rocm-omnivoice-cpp default: cpu-omnivoice-cpp intel: intel-sycl-f16-omnivoice-cpp metal: metal-omnivoice-cpp nvidia: cuda12-omnivoice-cpp nvidia-cuda-12: cuda12-omnivoice-cpp nvidia-cuda-13: cuda13-omnivoice-cpp nvidia-l4t: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-omnivoice-cpp vulkan: vulkan-omnivoice-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-omnivoice-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-omnivoice-cpp - name: rocm-omnivoice-cpp-development alias: omnivoice-cpp description: | OmniVoice C++ backend using GGML. Native text-to-speech with voice cloning (reference audio + transcript) and voice design (attribute keywords: gender, age, pitch, style, volume, emotion). 24kHz mono output, 646 languages. Supports streaming synthesis. urls: - https://github.com/ServeurpersoCom/omnivoice.cpp tags: - text-to-speech - tts - voice-cloning - voice-design capabilities: amd: rocm-omnivoice-cpp default: cpu-omnivoice-cpp intel: intel-sycl-f16-omnivoice-cpp metal: metal-omnivoice-cpp nvidia: cuda12-omnivoice-cpp nvidia-cuda-12: cuda12-omnivoice-cpp nvidia-cuda-13: cuda13-omnivoice-cpp nvidia-l4t: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-omnivoice-cpp vulkan: vulkan-omnivoice-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-omnivoice-cpp mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-omnivoice-cpp - name: intel-sycl-f32-omnivoice-cpp-development alias: omnivoice-cpp description: | OmniVoice C++ backend using GGML. Native text-to-speech with voice cloning (reference audio + transcript) and voice design (attribute keywords: gender, age, pitch, style, volume, emotion). 24kHz mono output, 646 languages. Supports streaming synthesis. urls: - https://github.com/ServeurpersoCom/omnivoice.cpp tags: - text-to-speech - tts - voice-cloning - voice-design capabilities: amd: rocm-omnivoice-cpp default: cpu-omnivoice-cpp intel: intel-sycl-f16-omnivoice-cpp metal: metal-omnivoice-cpp nvidia: cuda12-omnivoice-cpp nvidia-cuda-12: cuda12-omnivoice-cpp nvidia-cuda-13: cuda13-omnivoice-cpp nvidia-l4t: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-omnivoice-cpp vulkan: vulkan-omnivoice-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-omnivoice-cpp mirrors: - localai/localai-backends:master-gpu-intel-sycl-f32-omnivoice-cpp - name: intel-sycl-f16-omnivoice-cpp-development alias: omnivoice-cpp description: | OmniVoice C++ backend using GGML. Native text-to-speech with voice cloning (reference audio + transcript) and voice design (attribute keywords: gender, age, pitch, style, volume, emotion). 24kHz mono output, 646 languages. Supports streaming synthesis. urls: - https://github.com/ServeurpersoCom/omnivoice.cpp tags: - text-to-speech - tts - voice-cloning - voice-design capabilities: amd: rocm-omnivoice-cpp default: cpu-omnivoice-cpp intel: intel-sycl-f16-omnivoice-cpp metal: metal-omnivoice-cpp nvidia: cuda12-omnivoice-cpp nvidia-cuda-12: cuda12-omnivoice-cpp nvidia-cuda-13: cuda13-omnivoice-cpp nvidia-l4t: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-omnivoice-cpp vulkan: vulkan-omnivoice-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-omnivoice-cpp mirrors: - localai/localai-backends:master-gpu-intel-sycl-f16-omnivoice-cpp - name: cuda13-omnivoice-cpp alias: omnivoice-cpp description: | OmniVoice C++ backend using GGML. Native text-to-speech with voice cloning (reference audio + transcript) and voice design (attribute keywords: gender, age, pitch, style, volume, emotion). 24kHz mono output, 646 languages. Supports streaming synthesis. urls: - https://github.com/ServeurpersoCom/omnivoice.cpp tags: - text-to-speech - tts - voice-cloning - voice-design capabilities: amd: rocm-omnivoice-cpp default: cpu-omnivoice-cpp intel: intel-sycl-f16-omnivoice-cpp metal: metal-omnivoice-cpp nvidia: cuda12-omnivoice-cpp nvidia-cuda-12: cuda12-omnivoice-cpp nvidia-cuda-13: cuda13-omnivoice-cpp nvidia-l4t: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-omnivoice-cpp vulkan: vulkan-omnivoice-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-omnivoice-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-omnivoice-cpp - name: cuda13-omnivoice-cpp-development alias: omnivoice-cpp description: | OmniVoice C++ backend using GGML. Native text-to-speech with voice cloning (reference audio + transcript) and voice design (attribute keywords: gender, age, pitch, style, volume, emotion). 24kHz mono output, 646 languages. Supports streaming synthesis. urls: - https://github.com/ServeurpersoCom/omnivoice.cpp tags: - text-to-speech - tts - voice-cloning - voice-design capabilities: amd: rocm-omnivoice-cpp default: cpu-omnivoice-cpp intel: intel-sycl-f16-omnivoice-cpp metal: metal-omnivoice-cpp nvidia: cuda12-omnivoice-cpp nvidia-cuda-12: cuda12-omnivoice-cpp nvidia-cuda-13: cuda13-omnivoice-cpp nvidia-l4t: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-omnivoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-omnivoice-cpp vulkan: vulkan-omnivoice-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-omnivoice-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-omnivoice-cpp - name: nvidia-l4t-arm64-vibevoice-cpp alias: vibevoice-cpp description: | vibevoice.cpp C++ backend using GGML. Native C++ port of Microsoft VibeVoice for both text-to-speech (with voice cloning via voice prompt GGUFs) and long-form ASR with speaker diarization. Outputs 24kHz mono WAV; ASR returns per-speaker JSON segments. urls: - https://github.com/mudler/vibevoice.cpp tags: - text-to-speech - tts - speech-to-text - asr - voice-cloning - diarization capabilities: amd: rocm-vibevoice-cpp default: cpu-vibevoice-cpp intel: intel-sycl-f16-vibevoice-cpp metal: metal-vibevoice-cpp nvidia: cuda12-vibevoice-cpp nvidia-cuda-12: cuda12-vibevoice-cpp nvidia-cuda-13: cuda13-vibevoice-cpp nvidia-l4t: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice-cpp vulkan: vulkan-vibevoice-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-vibevoice-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-arm64-vibevoice-cpp - name: nvidia-l4t-arm64-vibevoice-cpp-development alias: vibevoice-cpp description: | vibevoice.cpp C++ backend using GGML. Native C++ port of Microsoft VibeVoice for both text-to-speech (with voice cloning via voice prompt GGUFs) and long-form ASR with speaker diarization. Outputs 24kHz mono WAV; ASR returns per-speaker JSON segments. urls: - https://github.com/mudler/vibevoice.cpp tags: - text-to-speech - tts - speech-to-text - asr - voice-cloning - diarization capabilities: amd: rocm-vibevoice-cpp default: cpu-vibevoice-cpp intel: intel-sycl-f16-vibevoice-cpp metal: metal-vibevoice-cpp nvidia: cuda12-vibevoice-cpp nvidia-cuda-12: cuda12-vibevoice-cpp nvidia-cuda-13: cuda13-vibevoice-cpp nvidia-l4t: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice-cpp vulkan: vulkan-vibevoice-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-vibevoice-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-arm64-vibevoice-cpp - name: cuda13-nvidia-l4t-arm64-vibevoice-cpp alias: vibevoice-cpp description: | vibevoice.cpp C++ backend using GGML. Native C++ port of Microsoft VibeVoice for both text-to-speech (with voice cloning via voice prompt GGUFs) and long-form ASR with speaker diarization. Outputs 24kHz mono WAV; ASR returns per-speaker JSON segments. urls: - https://github.com/mudler/vibevoice.cpp tags: - text-to-speech - tts - speech-to-text - asr - voice-cloning - diarization capabilities: amd: rocm-vibevoice-cpp default: cpu-vibevoice-cpp intel: intel-sycl-f16-vibevoice-cpp metal: metal-vibevoice-cpp nvidia: cuda12-vibevoice-cpp nvidia-cuda-12: cuda12-vibevoice-cpp nvidia-cuda-13: cuda13-vibevoice-cpp nvidia-l4t: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice-cpp vulkan: vulkan-vibevoice-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-vibevoice-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-vibevoice-cpp - name: cuda13-nvidia-l4t-arm64-vibevoice-cpp-development alias: vibevoice-cpp description: | vibevoice.cpp C++ backend using GGML. Native C++ port of Microsoft VibeVoice for both text-to-speech (with voice cloning via voice prompt GGUFs) and long-form ASR with speaker diarization. Outputs 24kHz mono WAV; ASR returns per-speaker JSON segments. urls: - https://github.com/mudler/vibevoice.cpp tags: - text-to-speech - tts - speech-to-text - asr - voice-cloning - diarization capabilities: amd: rocm-vibevoice-cpp default: cpu-vibevoice-cpp intel: intel-sycl-f16-vibevoice-cpp metal: metal-vibevoice-cpp nvidia: cuda12-vibevoice-cpp nvidia-cuda-12: cuda12-vibevoice-cpp nvidia-cuda-13: cuda13-vibevoice-cpp nvidia-l4t: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice-cpp vulkan: vulkan-vibevoice-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-vibevoice-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-vibevoice-cpp - name: cpu-vibevoice-cpp alias: vibevoice-cpp description: | vibevoice.cpp C++ backend using GGML. Native C++ port of Microsoft VibeVoice for both text-to-speech (with voice cloning via voice prompt GGUFs) and long-form ASR with speaker diarization. Outputs 24kHz mono WAV; ASR returns per-speaker JSON segments. urls: - https://github.com/mudler/vibevoice.cpp tags: - text-to-speech - tts - speech-to-text - asr - voice-cloning - diarization capabilities: amd: rocm-vibevoice-cpp default: cpu-vibevoice-cpp intel: intel-sycl-f16-vibevoice-cpp metal: metal-vibevoice-cpp nvidia: cuda12-vibevoice-cpp nvidia-cuda-12: cuda12-vibevoice-cpp nvidia-cuda-13: cuda13-vibevoice-cpp nvidia-l4t: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice-cpp vulkan: vulkan-vibevoice-cpp uri: quay.io/go-skynet/local-ai-backends:latest-cpu-vibevoice-cpp mirrors: - localai/localai-backends:latest-cpu-vibevoice-cpp - name: metal-vibevoice-cpp alias: vibevoice-cpp description: | vibevoice.cpp C++ backend using GGML. Native C++ port of Microsoft VibeVoice for both text-to-speech (with voice cloning via voice prompt GGUFs) and long-form ASR with speaker diarization. Outputs 24kHz mono WAV; ASR returns per-speaker JSON segments. urls: - https://github.com/mudler/vibevoice.cpp tags: - text-to-speech - tts - speech-to-text - asr - voice-cloning - diarization capabilities: amd: rocm-vibevoice-cpp default: cpu-vibevoice-cpp intel: intel-sycl-f16-vibevoice-cpp metal: metal-vibevoice-cpp nvidia: cuda12-vibevoice-cpp nvidia-cuda-12: cuda12-vibevoice-cpp nvidia-cuda-13: cuda13-vibevoice-cpp nvidia-l4t: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice-cpp vulkan: vulkan-vibevoice-cpp uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-vibevoice-cpp mirrors: - localai/localai-backends:latest-metal-darwin-arm64-vibevoice-cpp - name: metal-vibevoice-cpp-development alias: vibevoice-cpp description: | vibevoice.cpp C++ backend using GGML. Native C++ port of Microsoft VibeVoice for both text-to-speech (with voice cloning via voice prompt GGUFs) and long-form ASR with speaker diarization. Outputs 24kHz mono WAV; ASR returns per-speaker JSON segments. urls: - https://github.com/mudler/vibevoice.cpp tags: - text-to-speech - tts - speech-to-text - asr - voice-cloning - diarization capabilities: amd: rocm-vibevoice-cpp default: cpu-vibevoice-cpp intel: intel-sycl-f16-vibevoice-cpp metal: metal-vibevoice-cpp nvidia: cuda12-vibevoice-cpp nvidia-cuda-12: cuda12-vibevoice-cpp nvidia-cuda-13: cuda13-vibevoice-cpp nvidia-l4t: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice-cpp vulkan: vulkan-vibevoice-cpp uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-vibevoice-cpp mirrors: - localai/localai-backends:master-metal-darwin-arm64-vibevoice-cpp - name: cpu-vibevoice-cpp-development alias: vibevoice-cpp description: | vibevoice.cpp C++ backend using GGML. Native C++ port of Microsoft VibeVoice for both text-to-speech (with voice cloning via voice prompt GGUFs) and long-form ASR with speaker diarization. Outputs 24kHz mono WAV; ASR returns per-speaker JSON segments. urls: - https://github.com/mudler/vibevoice.cpp tags: - text-to-speech - tts - speech-to-text - asr - voice-cloning - diarization capabilities: amd: rocm-vibevoice-cpp default: cpu-vibevoice-cpp intel: intel-sycl-f16-vibevoice-cpp metal: metal-vibevoice-cpp nvidia: cuda12-vibevoice-cpp nvidia-cuda-12: cuda12-vibevoice-cpp nvidia-cuda-13: cuda13-vibevoice-cpp nvidia-l4t: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice-cpp vulkan: vulkan-vibevoice-cpp uri: quay.io/go-skynet/local-ai-backends:master-cpu-vibevoice-cpp mirrors: - localai/localai-backends:master-cpu-vibevoice-cpp - name: cuda12-vibevoice-cpp alias: vibevoice-cpp description: | vibevoice.cpp C++ backend using GGML. Native C++ port of Microsoft VibeVoice for both text-to-speech (with voice cloning via voice prompt GGUFs) and long-form ASR with speaker diarization. Outputs 24kHz mono WAV; ASR returns per-speaker JSON segments. urls: - https://github.com/mudler/vibevoice.cpp tags: - text-to-speech - tts - speech-to-text - asr - voice-cloning - diarization capabilities: amd: rocm-vibevoice-cpp default: cpu-vibevoice-cpp intel: intel-sycl-f16-vibevoice-cpp metal: metal-vibevoice-cpp nvidia: cuda12-vibevoice-cpp nvidia-cuda-12: cuda12-vibevoice-cpp nvidia-cuda-13: cuda13-vibevoice-cpp nvidia-l4t: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice-cpp vulkan: vulkan-vibevoice-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-vibevoice-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-vibevoice-cpp - name: rocm-vibevoice-cpp alias: vibevoice-cpp description: | vibevoice.cpp C++ backend using GGML. Native C++ port of Microsoft VibeVoice for both text-to-speech (with voice cloning via voice prompt GGUFs) and long-form ASR with speaker diarization. Outputs 24kHz mono WAV; ASR returns per-speaker JSON segments. urls: - https://github.com/mudler/vibevoice.cpp tags: - text-to-speech - tts - speech-to-text - asr - voice-cloning - diarization capabilities: amd: rocm-vibevoice-cpp default: cpu-vibevoice-cpp intel: intel-sycl-f16-vibevoice-cpp metal: metal-vibevoice-cpp nvidia: cuda12-vibevoice-cpp nvidia-cuda-12: cuda12-vibevoice-cpp nvidia-cuda-13: cuda13-vibevoice-cpp nvidia-l4t: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice-cpp vulkan: vulkan-vibevoice-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-vibevoice-cpp mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-vibevoice-cpp - name: intel-sycl-f32-vibevoice-cpp alias: vibevoice-cpp description: | vibevoice.cpp C++ backend using GGML. Native C++ port of Microsoft VibeVoice for both text-to-speech (with voice cloning via voice prompt GGUFs) and long-form ASR with speaker diarization. Outputs 24kHz mono WAV; ASR returns per-speaker JSON segments. urls: - https://github.com/mudler/vibevoice.cpp tags: - text-to-speech - tts - speech-to-text - asr - voice-cloning - diarization capabilities: amd: rocm-vibevoice-cpp default: cpu-vibevoice-cpp intel: intel-sycl-f16-vibevoice-cpp metal: metal-vibevoice-cpp nvidia: cuda12-vibevoice-cpp nvidia-cuda-12: cuda12-vibevoice-cpp nvidia-cuda-13: cuda13-vibevoice-cpp nvidia-l4t: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice-cpp vulkan: vulkan-vibevoice-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-vibevoice-cpp mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f32-vibevoice-cpp - name: intel-sycl-f16-vibevoice-cpp alias: vibevoice-cpp description: | vibevoice.cpp C++ backend using GGML. Native C++ port of Microsoft VibeVoice for both text-to-speech (with voice cloning via voice prompt GGUFs) and long-form ASR with speaker diarization. Outputs 24kHz mono WAV; ASR returns per-speaker JSON segments. urls: - https://github.com/mudler/vibevoice.cpp tags: - text-to-speech - tts - speech-to-text - asr - voice-cloning - diarization capabilities: amd: rocm-vibevoice-cpp default: cpu-vibevoice-cpp intel: intel-sycl-f16-vibevoice-cpp metal: metal-vibevoice-cpp nvidia: cuda12-vibevoice-cpp nvidia-cuda-12: cuda12-vibevoice-cpp nvidia-cuda-13: cuda13-vibevoice-cpp nvidia-l4t: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice-cpp vulkan: vulkan-vibevoice-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-vibevoice-cpp mirrors: - localai/localai-backends:latest-gpu-intel-sycl-f16-vibevoice-cpp - name: vulkan-vibevoice-cpp alias: vibevoice-cpp description: | vibevoice.cpp C++ backend using GGML. Native C++ port of Microsoft VibeVoice for both text-to-speech (with voice cloning via voice prompt GGUFs) and long-form ASR with speaker diarization. Outputs 24kHz mono WAV; ASR returns per-speaker JSON segments. urls: - https://github.com/mudler/vibevoice.cpp tags: - text-to-speech - tts - speech-to-text - asr - voice-cloning - diarization capabilities: amd: rocm-vibevoice-cpp default: cpu-vibevoice-cpp intel: intel-sycl-f16-vibevoice-cpp metal: metal-vibevoice-cpp nvidia: cuda12-vibevoice-cpp nvidia-cuda-12: cuda12-vibevoice-cpp nvidia-cuda-13: cuda13-vibevoice-cpp nvidia-l4t: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice-cpp vulkan: vulkan-vibevoice-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-vibevoice-cpp mirrors: - localai/localai-backends:latest-gpu-vulkan-vibevoice-cpp - name: vulkan-vibevoice-cpp-development alias: vibevoice-cpp description: | vibevoice.cpp C++ backend using GGML. Native C++ port of Microsoft VibeVoice for both text-to-speech (with voice cloning via voice prompt GGUFs) and long-form ASR with speaker diarization. Outputs 24kHz mono WAV; ASR returns per-speaker JSON segments. urls: - https://github.com/mudler/vibevoice.cpp tags: - text-to-speech - tts - speech-to-text - asr - voice-cloning - diarization capabilities: amd: rocm-vibevoice-cpp default: cpu-vibevoice-cpp intel: intel-sycl-f16-vibevoice-cpp metal: metal-vibevoice-cpp nvidia: cuda12-vibevoice-cpp nvidia-cuda-12: cuda12-vibevoice-cpp nvidia-cuda-13: cuda13-vibevoice-cpp nvidia-l4t: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice-cpp vulkan: vulkan-vibevoice-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-vibevoice-cpp mirrors: - localai/localai-backends:master-gpu-vulkan-vibevoice-cpp - name: cuda12-vibevoice-cpp-development alias: vibevoice-cpp description: | vibevoice.cpp C++ backend using GGML. Native C++ port of Microsoft VibeVoice for both text-to-speech (with voice cloning via voice prompt GGUFs) and long-form ASR with speaker diarization. Outputs 24kHz mono WAV; ASR returns per-speaker JSON segments. urls: - https://github.com/mudler/vibevoice.cpp tags: - text-to-speech - tts - speech-to-text - asr - voice-cloning - diarization capabilities: amd: rocm-vibevoice-cpp default: cpu-vibevoice-cpp intel: intel-sycl-f16-vibevoice-cpp metal: metal-vibevoice-cpp nvidia: cuda12-vibevoice-cpp nvidia-cuda-12: cuda12-vibevoice-cpp nvidia-cuda-13: cuda13-vibevoice-cpp nvidia-l4t: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice-cpp vulkan: vulkan-vibevoice-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-vibevoice-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-vibevoice-cpp - name: rocm-vibevoice-cpp-development alias: vibevoice-cpp description: | vibevoice.cpp C++ backend using GGML. Native C++ port of Microsoft VibeVoice for both text-to-speech (with voice cloning via voice prompt GGUFs) and long-form ASR with speaker diarization. Outputs 24kHz mono WAV; ASR returns per-speaker JSON segments. urls: - https://github.com/mudler/vibevoice.cpp tags: - text-to-speech - tts - speech-to-text - asr - voice-cloning - diarization capabilities: amd: rocm-vibevoice-cpp default: cpu-vibevoice-cpp intel: intel-sycl-f16-vibevoice-cpp metal: metal-vibevoice-cpp nvidia: cuda12-vibevoice-cpp nvidia-cuda-12: cuda12-vibevoice-cpp nvidia-cuda-13: cuda13-vibevoice-cpp nvidia-l4t: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice-cpp vulkan: vulkan-vibevoice-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-vibevoice-cpp mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-vibevoice-cpp - name: intel-sycl-f32-vibevoice-cpp-development alias: vibevoice-cpp description: | vibevoice.cpp C++ backend using GGML. Native C++ port of Microsoft VibeVoice for both text-to-speech (with voice cloning via voice prompt GGUFs) and long-form ASR with speaker diarization. Outputs 24kHz mono WAV; ASR returns per-speaker JSON segments. urls: - https://github.com/mudler/vibevoice.cpp tags: - text-to-speech - tts - speech-to-text - asr - voice-cloning - diarization capabilities: amd: rocm-vibevoice-cpp default: cpu-vibevoice-cpp intel: intel-sycl-f16-vibevoice-cpp metal: metal-vibevoice-cpp nvidia: cuda12-vibevoice-cpp nvidia-cuda-12: cuda12-vibevoice-cpp nvidia-cuda-13: cuda13-vibevoice-cpp nvidia-l4t: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice-cpp vulkan: vulkan-vibevoice-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-vibevoice-cpp mirrors: - localai/localai-backends:master-gpu-intel-sycl-f32-vibevoice-cpp - name: intel-sycl-f16-vibevoice-cpp-development alias: vibevoice-cpp description: | vibevoice.cpp C++ backend using GGML. Native C++ port of Microsoft VibeVoice for both text-to-speech (with voice cloning via voice prompt GGUFs) and long-form ASR with speaker diarization. Outputs 24kHz mono WAV; ASR returns per-speaker JSON segments. urls: - https://github.com/mudler/vibevoice.cpp tags: - text-to-speech - tts - speech-to-text - asr - voice-cloning - diarization capabilities: amd: rocm-vibevoice-cpp default: cpu-vibevoice-cpp intel: intel-sycl-f16-vibevoice-cpp metal: metal-vibevoice-cpp nvidia: cuda12-vibevoice-cpp nvidia-cuda-12: cuda12-vibevoice-cpp nvidia-cuda-13: cuda13-vibevoice-cpp nvidia-l4t: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice-cpp vulkan: vulkan-vibevoice-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-vibevoice-cpp mirrors: - localai/localai-backends:master-gpu-intel-sycl-f16-vibevoice-cpp - name: cuda13-vibevoice-cpp alias: vibevoice-cpp description: | vibevoice.cpp C++ backend using GGML. Native C++ port of Microsoft VibeVoice for both text-to-speech (with voice cloning via voice prompt GGUFs) and long-form ASR with speaker diarization. Outputs 24kHz mono WAV; ASR returns per-speaker JSON segments. urls: - https://github.com/mudler/vibevoice.cpp tags: - text-to-speech - tts - speech-to-text - asr - voice-cloning - diarization capabilities: amd: rocm-vibevoice-cpp default: cpu-vibevoice-cpp intel: intel-sycl-f16-vibevoice-cpp metal: metal-vibevoice-cpp nvidia: cuda12-vibevoice-cpp nvidia-cuda-12: cuda12-vibevoice-cpp nvidia-cuda-13: cuda13-vibevoice-cpp nvidia-l4t: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice-cpp vulkan: vulkan-vibevoice-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-vibevoice-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-vibevoice-cpp - name: cuda13-vibevoice-cpp-development alias: vibevoice-cpp description: | vibevoice.cpp C++ backend using GGML. Native C++ port of Microsoft VibeVoice for both text-to-speech (with voice cloning via voice prompt GGUFs) and long-form ASR with speaker diarization. Outputs 24kHz mono WAV; ASR returns per-speaker JSON segments. urls: - https://github.com/mudler/vibevoice.cpp tags: - text-to-speech - tts - speech-to-text - asr - voice-cloning - diarization capabilities: amd: rocm-vibevoice-cpp default: cpu-vibevoice-cpp intel: intel-sycl-f16-vibevoice-cpp metal: metal-vibevoice-cpp nvidia: cuda12-vibevoice-cpp nvidia-cuda-12: cuda12-vibevoice-cpp nvidia-cuda-13: cuda13-vibevoice-cpp nvidia-l4t: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-12: nvidia-l4t-arm64-vibevoice-cpp nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice-cpp vulkan: vulkan-vibevoice-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-vibevoice-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-vibevoice-cpp - name: cpu-localvqe alias: localvqe license: apache2 description: | LocalVQE C++ backend using GGML — joint acoustic echo cancellation, noise suppression, and dereverberation (DeepVQE-style architecture). 16 kHz mono in / out, supports both batch and low-latency streaming. Implements the audio-transform capability. urls: - https://github.com/localai-org/LocalVQE tags: - audio-transform - aec - acoustic-echo-cancellation - noise-suppression - dereverberation capabilities: amd: vulkan-localvqe default: cpu-localvqe intel: vulkan-localvqe metal: metal-localvqe nvidia: vulkan-localvqe nvidia-cuda-12: vulkan-localvqe nvidia-cuda-13: vulkan-localvqe nvidia-l4t: vulkan-localvqe nvidia-l4t-cuda-12: vulkan-localvqe nvidia-l4t-cuda-13: vulkan-localvqe vulkan: vulkan-localvqe uri: quay.io/go-skynet/local-ai-backends:latest-cpu-localvqe mirrors: - localai/localai-backends:latest-cpu-localvqe - name: cpu-localvqe-development alias: localvqe license: apache2 description: | LocalVQE C++ backend using GGML — joint acoustic echo cancellation, noise suppression, and dereverberation (DeepVQE-style architecture). 16 kHz mono in / out, supports both batch and low-latency streaming. Implements the audio-transform capability. urls: - https://github.com/localai-org/LocalVQE tags: - audio-transform - aec - acoustic-echo-cancellation - noise-suppression - dereverberation capabilities: amd: vulkan-localvqe default: cpu-localvqe intel: vulkan-localvqe metal: metal-localvqe nvidia: vulkan-localvqe nvidia-cuda-12: vulkan-localvqe nvidia-cuda-13: vulkan-localvqe nvidia-l4t: vulkan-localvqe nvidia-l4t-cuda-12: vulkan-localvqe nvidia-l4t-cuda-13: vulkan-localvqe vulkan: vulkan-localvqe uri: quay.io/go-skynet/local-ai-backends:master-cpu-localvqe mirrors: - localai/localai-backends:master-cpu-localvqe - name: vulkan-localvqe alias: localvqe license: apache2 description: | LocalVQE C++ backend using GGML — joint acoustic echo cancellation, noise suppression, and dereverberation (DeepVQE-style architecture). 16 kHz mono in / out, supports both batch and low-latency streaming. Implements the audio-transform capability. urls: - https://github.com/localai-org/LocalVQE tags: - audio-transform - aec - acoustic-echo-cancellation - noise-suppression - dereverberation capabilities: amd: vulkan-localvqe default: cpu-localvqe intel: vulkan-localvqe metal: metal-localvqe nvidia: vulkan-localvqe nvidia-cuda-12: vulkan-localvqe nvidia-cuda-13: vulkan-localvqe nvidia-l4t: vulkan-localvqe nvidia-l4t-cuda-12: vulkan-localvqe nvidia-l4t-cuda-13: vulkan-localvqe vulkan: vulkan-localvqe uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-localvqe mirrors: - localai/localai-backends:latest-gpu-vulkan-localvqe - name: vulkan-localvqe-development alias: localvqe license: apache2 description: | LocalVQE C++ backend using GGML — joint acoustic echo cancellation, noise suppression, and dereverberation (DeepVQE-style architecture). 16 kHz mono in / out, supports both batch and low-latency streaming. Implements the audio-transform capability. urls: - https://github.com/localai-org/LocalVQE tags: - audio-transform - aec - acoustic-echo-cancellation - noise-suppression - dereverberation capabilities: amd: vulkan-localvqe default: cpu-localvqe intel: vulkan-localvqe metal: metal-localvqe nvidia: vulkan-localvqe nvidia-cuda-12: vulkan-localvqe nvidia-cuda-13: vulkan-localvqe nvidia-l4t: vulkan-localvqe nvidia-l4t-cuda-12: vulkan-localvqe nvidia-l4t-cuda-13: vulkan-localvqe vulkan: vulkan-localvqe uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-localvqe mirrors: - localai/localai-backends:master-gpu-vulkan-localvqe - name: metal-localvqe alias: localvqe license: apache2 description: | LocalVQE C++ backend using GGML — joint acoustic echo cancellation, noise suppression, and dereverberation (DeepVQE-style architecture). 16 kHz mono in / out, supports both batch and low-latency streaming. Implements the audio-transform capability. urls: - https://github.com/localai-org/LocalVQE tags: - audio-transform - aec - acoustic-echo-cancellation - noise-suppression - dereverberation capabilities: amd: vulkan-localvqe default: cpu-localvqe intel: vulkan-localvqe metal: metal-localvqe nvidia: vulkan-localvqe nvidia-cuda-12: vulkan-localvqe nvidia-cuda-13: vulkan-localvqe nvidia-l4t: vulkan-localvqe nvidia-l4t-cuda-12: vulkan-localvqe nvidia-l4t-cuda-13: vulkan-localvqe vulkan: vulkan-localvqe uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-localvqe mirrors: - localai/localai-backends:latest-metal-darwin-arm64-localvqe - name: metal-localvqe-development alias: localvqe license: apache2 description: | LocalVQE C++ backend using GGML — joint acoustic echo cancellation, noise suppression, and dereverberation (DeepVQE-style architecture). 16 kHz mono in / out, supports both batch and low-latency streaming. Implements the audio-transform capability. urls: - https://github.com/localai-org/LocalVQE tags: - audio-transform - aec - acoustic-echo-cancellation - noise-suppression - dereverberation capabilities: amd: vulkan-localvqe default: cpu-localvqe intel: vulkan-localvqe metal: metal-localvqe nvidia: vulkan-localvqe nvidia-cuda-12: vulkan-localvqe nvidia-cuda-13: vulkan-localvqe nvidia-l4t: vulkan-localvqe nvidia-l4t-cuda-12: vulkan-localvqe nvidia-l4t-cuda-13: vulkan-localvqe vulkan: vulkan-localvqe uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-localvqe mirrors: - localai/localai-backends:master-metal-darwin-arm64-localvqe - name: kokoro-development alias: kokoro license: apache-2.0 icon: https://avatars.githubusercontent.com/u/166769057?v=4 description: | Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects. urls: - https://huggingface.co/hexgrad/Kokoro-82M - https://github.com/hexgrad/kokoro tags: - text-to-speech - TTS - LLM capabilities: amd: rocm-kokoro-development default: cpu-kokoro-development intel: intel-kokoro-development metal: metal-kokoro-development nvidia: cuda12-kokoro-development nvidia-l4t: nvidia-l4t-kokoro-development - name: cpu-kokoro alias: kokoro license: apache-2.0 icon: https://avatars.githubusercontent.com/u/166769057?v=4 description: | Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects. urls: - https://huggingface.co/hexgrad/Kokoro-82M - https://github.com/hexgrad/kokoro tags: - text-to-speech - TTS - LLM capabilities: amd: rocm-kokoro default: cpu-kokoro intel: intel-kokoro metal: metal-kokoro nvidia: cuda12-kokoro nvidia-cuda-12: cuda12-kokoro nvidia-cuda-13: cuda13-kokoro nvidia-l4t: nvidia-l4t-kokoro nvidia-l4t-cuda-12: nvidia-l4t-kokoro uri: quay.io/go-skynet/local-ai-backends:latest-cpu-kokoro mirrors: - localai/localai-backends:latest-cpu-kokoro - name: cpu-kokoro-development alias: kokoro license: apache-2.0 icon: https://avatars.githubusercontent.com/u/166769057?v=4 description: | Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects. urls: - https://huggingface.co/hexgrad/Kokoro-82M - https://github.com/hexgrad/kokoro tags: - text-to-speech - TTS - LLM capabilities: amd: rocm-kokoro default: cpu-kokoro intel: intel-kokoro metal: metal-kokoro nvidia: cuda12-kokoro nvidia-cuda-12: cuda12-kokoro nvidia-cuda-13: cuda13-kokoro nvidia-l4t: nvidia-l4t-kokoro nvidia-l4t-cuda-12: nvidia-l4t-kokoro uri: quay.io/go-skynet/local-ai-backends:master-cpu-kokoro mirrors: - localai/localai-backends:master-cpu-kokoro - name: cuda12-kokoro-development alias: kokoro license: apache-2.0 icon: https://avatars.githubusercontent.com/u/166769057?v=4 description: | Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects. urls: - https://huggingface.co/hexgrad/Kokoro-82M - https://github.com/hexgrad/kokoro tags: - text-to-speech - TTS - LLM capabilities: amd: rocm-kokoro default: cpu-kokoro intel: intel-kokoro metal: metal-kokoro nvidia: cuda12-kokoro nvidia-cuda-12: cuda12-kokoro nvidia-cuda-13: cuda13-kokoro nvidia-l4t: nvidia-l4t-kokoro nvidia-l4t-cuda-12: nvidia-l4t-kokoro uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-kokoro mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-kokoro - name: rocm-kokoro-development alias: kokoro license: apache-2.0 icon: https://avatars.githubusercontent.com/u/166769057?v=4 description: | Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects. urls: - https://huggingface.co/hexgrad/Kokoro-82M - https://github.com/hexgrad/kokoro tags: - text-to-speech - TTS - LLM capabilities: amd: rocm-kokoro default: cpu-kokoro intel: intel-kokoro metal: metal-kokoro nvidia: cuda12-kokoro nvidia-cuda-12: cuda12-kokoro nvidia-cuda-13: cuda13-kokoro nvidia-l4t: nvidia-l4t-kokoro nvidia-l4t-cuda-12: nvidia-l4t-kokoro uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-kokoro mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-kokoro - name: intel-kokoro alias: kokoro license: apache-2.0 icon: https://avatars.githubusercontent.com/u/166769057?v=4 description: | Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects. urls: - https://huggingface.co/hexgrad/Kokoro-82M - https://github.com/hexgrad/kokoro tags: - text-to-speech - TTS - LLM capabilities: amd: rocm-kokoro default: cpu-kokoro intel: intel-kokoro metal: metal-kokoro nvidia: cuda12-kokoro nvidia-cuda-12: cuda12-kokoro nvidia-cuda-13: cuda13-kokoro nvidia-l4t: nvidia-l4t-kokoro nvidia-l4t-cuda-12: nvidia-l4t-kokoro uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-kokoro mirrors: - localai/localai-backends:latest-gpu-intel-kokoro - name: intel-kokoro-development alias: kokoro license: apache-2.0 icon: https://avatars.githubusercontent.com/u/166769057?v=4 description: | Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects. urls: - https://huggingface.co/hexgrad/Kokoro-82M - https://github.com/hexgrad/kokoro tags: - text-to-speech - TTS - LLM capabilities: amd: rocm-kokoro default: cpu-kokoro intel: intel-kokoro metal: metal-kokoro nvidia: cuda12-kokoro nvidia-cuda-12: cuda12-kokoro nvidia-cuda-13: cuda13-kokoro nvidia-l4t: nvidia-l4t-kokoro nvidia-l4t-cuda-12: nvidia-l4t-kokoro uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-kokoro mirrors: - localai/localai-backends:master-gpu-intel-kokoro - name: nvidia-l4t-kokoro alias: kokoro license: apache-2.0 icon: https://avatars.githubusercontent.com/u/166769057?v=4 description: | Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects. urls: - https://huggingface.co/hexgrad/Kokoro-82M - https://github.com/hexgrad/kokoro tags: - text-to-speech - TTS - LLM capabilities: amd: rocm-kokoro default: cpu-kokoro intel: intel-kokoro metal: metal-kokoro nvidia: cuda12-kokoro nvidia-cuda-12: cuda12-kokoro nvidia-cuda-13: cuda13-kokoro nvidia-l4t: nvidia-l4t-kokoro nvidia-l4t-cuda-12: nvidia-l4t-kokoro uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-kokoro mirrors: - localai/localai-backends:latest-nvidia-l4t-kokoro - name: nvidia-l4t-kokoro-development alias: kokoro license: apache-2.0 icon: https://avatars.githubusercontent.com/u/166769057?v=4 description: | Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects. urls: - https://huggingface.co/hexgrad/Kokoro-82M - https://github.com/hexgrad/kokoro tags: - text-to-speech - TTS - LLM capabilities: amd: rocm-kokoro default: cpu-kokoro intel: intel-kokoro metal: metal-kokoro nvidia: cuda12-kokoro nvidia-cuda-12: cuda12-kokoro nvidia-cuda-13: cuda13-kokoro nvidia-l4t: nvidia-l4t-kokoro nvidia-l4t-cuda-12: nvidia-l4t-kokoro uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-kokoro mirrors: - localai/localai-backends:master-nvidia-l4t-kokoro - name: cuda12-kokoro alias: kokoro license: apache-2.0 icon: https://avatars.githubusercontent.com/u/166769057?v=4 description: | Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects. urls: - https://huggingface.co/hexgrad/Kokoro-82M - https://github.com/hexgrad/kokoro tags: - text-to-speech - TTS - LLM capabilities: amd: rocm-kokoro default: cpu-kokoro intel: intel-kokoro metal: metal-kokoro nvidia: cuda12-kokoro nvidia-cuda-12: cuda12-kokoro nvidia-cuda-13: cuda13-kokoro nvidia-l4t: nvidia-l4t-kokoro nvidia-l4t-cuda-12: nvidia-l4t-kokoro uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-kokoro mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-kokoro - name: rocm-kokoro alias: kokoro license: apache-2.0 icon: https://avatars.githubusercontent.com/u/166769057?v=4 description: | Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects. urls: - https://huggingface.co/hexgrad/Kokoro-82M - https://github.com/hexgrad/kokoro tags: - text-to-speech - TTS - LLM capabilities: amd: rocm-kokoro default: cpu-kokoro intel: intel-kokoro metal: metal-kokoro nvidia: cuda12-kokoro nvidia-cuda-12: cuda12-kokoro nvidia-cuda-13: cuda13-kokoro nvidia-l4t: nvidia-l4t-kokoro nvidia-l4t-cuda-12: nvidia-l4t-kokoro uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-kokoro mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-kokoro - name: cuda13-kokoro alias: kokoro license: apache-2.0 icon: https://avatars.githubusercontent.com/u/166769057?v=4 description: | Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects. urls: - https://huggingface.co/hexgrad/Kokoro-82M - https://github.com/hexgrad/kokoro tags: - text-to-speech - TTS - LLM capabilities: amd: rocm-kokoro default: cpu-kokoro intel: intel-kokoro metal: metal-kokoro nvidia: cuda12-kokoro nvidia-cuda-12: cuda12-kokoro nvidia-cuda-13: cuda13-kokoro nvidia-l4t: nvidia-l4t-kokoro nvidia-l4t-cuda-12: nvidia-l4t-kokoro uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-kokoro mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-kokoro - name: cuda13-kokoro-development alias: kokoro license: apache-2.0 icon: https://avatars.githubusercontent.com/u/166769057?v=4 description: | Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects. urls: - https://huggingface.co/hexgrad/Kokoro-82M - https://github.com/hexgrad/kokoro tags: - text-to-speech - TTS - LLM capabilities: amd: rocm-kokoro default: cpu-kokoro intel: intel-kokoro metal: metal-kokoro nvidia: cuda12-kokoro nvidia-cuda-12: cuda12-kokoro nvidia-cuda-13: cuda13-kokoro nvidia-l4t: nvidia-l4t-kokoro nvidia-l4t-cuda-12: nvidia-l4t-kokoro uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-kokoro mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-kokoro - name: metal-kokoro alias: kokoro license: apache-2.0 icon: https://avatars.githubusercontent.com/u/166769057?v=4 description: | Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects. urls: - https://huggingface.co/hexgrad/Kokoro-82M - https://github.com/hexgrad/kokoro tags: - text-to-speech - TTS - LLM capabilities: amd: rocm-kokoro default: cpu-kokoro intel: intel-kokoro metal: metal-kokoro nvidia: cuda12-kokoro nvidia-cuda-12: cuda12-kokoro nvidia-cuda-13: cuda13-kokoro nvidia-l4t: nvidia-l4t-kokoro nvidia-l4t-cuda-12: nvidia-l4t-kokoro uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-kokoro mirrors: - localai/localai-backends:latest-metal-darwin-arm64-kokoro - name: metal-kokoro-development alias: kokoro license: apache-2.0 icon: https://avatars.githubusercontent.com/u/166769057?v=4 description: | Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects. urls: - https://huggingface.co/hexgrad/Kokoro-82M - https://github.com/hexgrad/kokoro tags: - text-to-speech - TTS - LLM capabilities: amd: rocm-kokoro default: cpu-kokoro intel: intel-kokoro metal: metal-kokoro nvidia: cuda12-kokoro nvidia-cuda-12: cuda12-kokoro nvidia-cuda-13: cuda13-kokoro nvidia-l4t: nvidia-l4t-kokoro nvidia-l4t-cuda-12: nvidia-l4t-kokoro uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-kokoro mirrors: - localai/localai-backends:master-metal-darwin-arm64-kokoro - name: kokoros-development alias: kokoros license: apache-2.0 icon: https://avatars.githubusercontent.com/u/166769057?v=4 description: | Kokoros is a pure Rust TTS backend using the Kokoro ONNX model (82M parameters). It provides fast, high-quality text-to-speech with streaming support, built on ONNX Runtime for efficient CPU inference. Supports English, Japanese, Mandarin Chinese, and German. urls: - https://huggingface.co/hexgrad/Kokoro-82M - https://github.com/lucasjinreal/Kokoros tags: - text-to-speech - TTS - Rust - ONNX capabilities: default: cpu-kokoros-development - name: cpu-kokoros alias: kokoros license: apache-2.0 icon: https://avatars.githubusercontent.com/u/166769057?v=4 description: | Kokoros is a pure Rust TTS backend using the Kokoro ONNX model (82M parameters). It provides fast, high-quality text-to-speech with streaming support, built on ONNX Runtime for efficient CPU inference. Supports English, Japanese, Mandarin Chinese, and German. urls: - https://huggingface.co/hexgrad/Kokoro-82M - https://github.com/lucasjinreal/Kokoros tags: - text-to-speech - TTS - Rust - ONNX capabilities: default: cpu-kokoros uri: quay.io/go-skynet/local-ai-backends:latest-cpu-kokoros mirrors: - localai/localai-backends:latest-cpu-kokoros - name: cpu-kokoros-development alias: kokoros license: apache-2.0 icon: https://avatars.githubusercontent.com/u/166769057?v=4 description: | Kokoros is a pure Rust TTS backend using the Kokoro ONNX model (82M parameters). It provides fast, high-quality text-to-speech with streaming support, built on ONNX Runtime for efficient CPU inference. Supports English, Japanese, Mandarin Chinese, and German. urls: - https://huggingface.co/hexgrad/Kokoro-82M - https://github.com/lucasjinreal/Kokoros tags: - text-to-speech - TTS - Rust - ONNX capabilities: default: cpu-kokoros uri: quay.io/go-skynet/local-ai-backends:master-cpu-kokoros mirrors: - localai/localai-backends:master-cpu-kokoros - name: faster-whisper-development license: MIT icon: https://avatars.githubusercontent.com/u/1520500?s=200&v=4 description: | faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models. This implementation is up to 4 times faster than openai/whisper for the same accuracy while using less memory. The efficiency can be further improved with 8-bit quantization on both CPU and GPU. urls: - https://github.com/SYSTRAN/faster-whisper tags: - speech-to-text - Whisper capabilities: amd: rocm-faster-whisper-development default: cpu-faster-whisper-development intel: intel-faster-whisper-development metal: metal-faster-whisper-development nvidia: cuda12-faster-whisper-development nvidia-cuda-13: cuda13-faster-whisper-development nvidia-l4t: nvidia-l4t-arm64-faster-whisper-development - name: cuda12-faster-whisper-development license: MIT icon: https://avatars.githubusercontent.com/u/1520500?s=200&v=4 description: | faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models. This implementation is up to 4 times faster than openai/whisper for the same accuracy while using less memory. The efficiency can be further improved with 8-bit quantization on both CPU and GPU. urls: - https://github.com/SYSTRAN/faster-whisper tags: - speech-to-text - Whisper capabilities: amd: rocm-faster-whisper default: cpu-faster-whisper intel: intel-faster-whisper metal: metal-faster-whisper nvidia: cuda12-faster-whisper nvidia-cuda-12: cuda12-faster-whisper nvidia-cuda-13: cuda13-faster-whisper nvidia-l4t: nvidia-l4t-arm64-faster-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-faster-whisper uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-faster-whisper mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-faster-whisper - name: rocm-faster-whisper-development license: MIT icon: https://avatars.githubusercontent.com/u/1520500?s=200&v=4 description: | faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models. This implementation is up to 4 times faster than openai/whisper for the same accuracy while using less memory. The efficiency can be further improved with 8-bit quantization on both CPU and GPU. urls: - https://github.com/SYSTRAN/faster-whisper tags: - speech-to-text - Whisper capabilities: amd: rocm-faster-whisper default: cpu-faster-whisper intel: intel-faster-whisper metal: metal-faster-whisper nvidia: cuda12-faster-whisper nvidia-cuda-12: cuda12-faster-whisper nvidia-cuda-13: cuda13-faster-whisper nvidia-l4t: nvidia-l4t-arm64-faster-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-faster-whisper uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-faster-whisper mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-faster-whisper - name: intel-faster-whisper license: MIT icon: https://avatars.githubusercontent.com/u/1520500?s=200&v=4 description: | faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models. This implementation is up to 4 times faster than openai/whisper for the same accuracy while using less memory. The efficiency can be further improved with 8-bit quantization on both CPU and GPU. urls: - https://github.com/SYSTRAN/faster-whisper tags: - speech-to-text - Whisper capabilities: amd: rocm-faster-whisper default: cpu-faster-whisper intel: intel-faster-whisper metal: metal-faster-whisper nvidia: cuda12-faster-whisper nvidia-cuda-12: cuda12-faster-whisper nvidia-cuda-13: cuda13-faster-whisper nvidia-l4t: nvidia-l4t-arm64-faster-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-faster-whisper uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-faster-whisper mirrors: - localai/localai-backends:latest-gpu-intel-faster-whisper - name: intel-faster-whisper-development license: MIT icon: https://avatars.githubusercontent.com/u/1520500?s=200&v=4 description: | faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models. This implementation is up to 4 times faster than openai/whisper for the same accuracy while using less memory. The efficiency can be further improved with 8-bit quantization on both CPU and GPU. urls: - https://github.com/SYSTRAN/faster-whisper tags: - speech-to-text - Whisper capabilities: amd: rocm-faster-whisper default: cpu-faster-whisper intel: intel-faster-whisper metal: metal-faster-whisper nvidia: cuda12-faster-whisper nvidia-cuda-12: cuda12-faster-whisper nvidia-cuda-13: cuda13-faster-whisper nvidia-l4t: nvidia-l4t-arm64-faster-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-faster-whisper uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-faster-whisper mirrors: - localai/localai-backends:master-gpu-intel-faster-whisper - name: cuda13-faster-whisper license: MIT icon: https://avatars.githubusercontent.com/u/1520500?s=200&v=4 description: | faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models. This implementation is up to 4 times faster than openai/whisper for the same accuracy while using less memory. The efficiency can be further improved with 8-bit quantization on both CPU and GPU. urls: - https://github.com/SYSTRAN/faster-whisper tags: - speech-to-text - Whisper capabilities: amd: rocm-faster-whisper default: cpu-faster-whisper intel: intel-faster-whisper metal: metal-faster-whisper nvidia: cuda12-faster-whisper nvidia-cuda-12: cuda12-faster-whisper nvidia-cuda-13: cuda13-faster-whisper nvidia-l4t: nvidia-l4t-arm64-faster-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-faster-whisper uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-faster-whisper mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-faster-whisper - name: cuda13-faster-whisper-development license: MIT icon: https://avatars.githubusercontent.com/u/1520500?s=200&v=4 description: | faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models. This implementation is up to 4 times faster than openai/whisper for the same accuracy while using less memory. The efficiency can be further improved with 8-bit quantization on both CPU and GPU. urls: - https://github.com/SYSTRAN/faster-whisper tags: - speech-to-text - Whisper capabilities: amd: rocm-faster-whisper default: cpu-faster-whisper intel: intel-faster-whisper metal: metal-faster-whisper nvidia: cuda12-faster-whisper nvidia-cuda-12: cuda12-faster-whisper nvidia-cuda-13: cuda13-faster-whisper nvidia-l4t: nvidia-l4t-arm64-faster-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-faster-whisper uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-faster-whisper mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-faster-whisper - name: metal-faster-whisper license: MIT icon: https://avatars.githubusercontent.com/u/1520500?s=200&v=4 description: | faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models. This implementation is up to 4 times faster than openai/whisper for the same accuracy while using less memory. The efficiency can be further improved with 8-bit quantization on both CPU and GPU. urls: - https://github.com/SYSTRAN/faster-whisper tags: - speech-to-text - Whisper capabilities: amd: rocm-faster-whisper default: cpu-faster-whisper intel: intel-faster-whisper metal: metal-faster-whisper nvidia: cuda12-faster-whisper nvidia-cuda-12: cuda12-faster-whisper nvidia-cuda-13: cuda13-faster-whisper nvidia-l4t: nvidia-l4t-arm64-faster-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-faster-whisper uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-faster-whisper mirrors: - localai/localai-backends:latest-metal-darwin-arm64-faster-whisper - name: metal-faster-whisper-development license: MIT icon: https://avatars.githubusercontent.com/u/1520500?s=200&v=4 description: | faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models. This implementation is up to 4 times faster than openai/whisper for the same accuracy while using less memory. The efficiency can be further improved with 8-bit quantization on both CPU and GPU. urls: - https://github.com/SYSTRAN/faster-whisper tags: - speech-to-text - Whisper capabilities: amd: rocm-faster-whisper default: cpu-faster-whisper intel: intel-faster-whisper metal: metal-faster-whisper nvidia: cuda12-faster-whisper nvidia-cuda-12: cuda12-faster-whisper nvidia-cuda-13: cuda13-faster-whisper nvidia-l4t: nvidia-l4t-arm64-faster-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-faster-whisper uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-faster-whisper mirrors: - localai/localai-backends:master-metal-darwin-arm64-faster-whisper - name: cuda12-faster-whisper license: MIT icon: https://avatars.githubusercontent.com/u/1520500?s=200&v=4 description: | faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models. This implementation is up to 4 times faster than openai/whisper for the same accuracy while using less memory. The efficiency can be further improved with 8-bit quantization on both CPU and GPU. urls: - https://github.com/SYSTRAN/faster-whisper tags: - speech-to-text - Whisper capabilities: amd: rocm-faster-whisper default: cpu-faster-whisper intel: intel-faster-whisper metal: metal-faster-whisper nvidia: cuda12-faster-whisper nvidia-cuda-12: cuda12-faster-whisper nvidia-cuda-13: cuda13-faster-whisper nvidia-l4t: nvidia-l4t-arm64-faster-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-faster-whisper uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-faster-whisper mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-faster-whisper - name: rocm-faster-whisper license: MIT icon: https://avatars.githubusercontent.com/u/1520500?s=200&v=4 description: | faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models. This implementation is up to 4 times faster than openai/whisper for the same accuracy while using less memory. The efficiency can be further improved with 8-bit quantization on both CPU and GPU. urls: - https://github.com/SYSTRAN/faster-whisper tags: - speech-to-text - Whisper capabilities: amd: rocm-faster-whisper default: cpu-faster-whisper intel: intel-faster-whisper metal: metal-faster-whisper nvidia: cuda12-faster-whisper nvidia-cuda-12: cuda12-faster-whisper nvidia-cuda-13: cuda13-faster-whisper nvidia-l4t: nvidia-l4t-arm64-faster-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-faster-whisper uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-faster-whisper mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-faster-whisper - name: cpu-faster-whisper license: MIT icon: https://avatars.githubusercontent.com/u/1520500?s=200&v=4 description: | faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models. This implementation is up to 4 times faster than openai/whisper for the same accuracy while using less memory. The efficiency can be further improved with 8-bit quantization on both CPU and GPU. urls: - https://github.com/SYSTRAN/faster-whisper tags: - speech-to-text - Whisper capabilities: amd: rocm-faster-whisper default: cpu-faster-whisper intel: intel-faster-whisper metal: metal-faster-whisper nvidia: cuda12-faster-whisper nvidia-cuda-12: cuda12-faster-whisper nvidia-cuda-13: cuda13-faster-whisper nvidia-l4t: nvidia-l4t-arm64-faster-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-faster-whisper uri: quay.io/go-skynet/local-ai-backends:latest-cpu-faster-whisper mirrors: - localai/localai-backends:latest-cpu-faster-whisper - name: cpu-faster-whisper-development license: MIT icon: https://avatars.githubusercontent.com/u/1520500?s=200&v=4 description: | faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models. This implementation is up to 4 times faster than openai/whisper for the same accuracy while using less memory. The efficiency can be further improved with 8-bit quantization on both CPU and GPU. urls: - https://github.com/SYSTRAN/faster-whisper tags: - speech-to-text - Whisper capabilities: amd: rocm-faster-whisper default: cpu-faster-whisper intel: intel-faster-whisper metal: metal-faster-whisper nvidia: cuda12-faster-whisper nvidia-cuda-12: cuda12-faster-whisper nvidia-cuda-13: cuda13-faster-whisper nvidia-l4t: nvidia-l4t-arm64-faster-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-faster-whisper uri: quay.io/go-skynet/local-ai-backends:master-cpu-faster-whisper mirrors: - localai/localai-backends:master-cpu-faster-whisper - name: nvidia-l4t-arm64-faster-whisper license: MIT icon: https://avatars.githubusercontent.com/u/1520500?s=200&v=4 description: | faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models. This implementation is up to 4 times faster than openai/whisper for the same accuracy while using less memory. The efficiency can be further improved with 8-bit quantization on both CPU and GPU. urls: - https://github.com/SYSTRAN/faster-whisper tags: - speech-to-text - Whisper capabilities: amd: rocm-faster-whisper default: cpu-faster-whisper intel: intel-faster-whisper metal: metal-faster-whisper nvidia: cuda12-faster-whisper nvidia-cuda-12: cuda12-faster-whisper nvidia-cuda-13: cuda13-faster-whisper nvidia-l4t: nvidia-l4t-arm64-faster-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-faster-whisper uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-faster-whisper mirrors: - localai/localai-backends:latest-nvidia-l4t-faster-whisper - name: nvidia-l4t-arm64-faster-whisper-development license: MIT icon: https://avatars.githubusercontent.com/u/1520500?s=200&v=4 description: | faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2, which is a fast inference engine for Transformer models. This implementation is up to 4 times faster than openai/whisper for the same accuracy while using less memory. The efficiency can be further improved with 8-bit quantization on both CPU and GPU. urls: - https://github.com/SYSTRAN/faster-whisper tags: - speech-to-text - Whisper capabilities: amd: rocm-faster-whisper default: cpu-faster-whisper intel: intel-faster-whisper metal: metal-faster-whisper nvidia: cuda12-faster-whisper nvidia-cuda-12: cuda12-faster-whisper nvidia-cuda-13: cuda13-faster-whisper nvidia-l4t: nvidia-l4t-arm64-faster-whisper nvidia-l4t-cuda-12: nvidia-l4t-arm64-faster-whisper uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-faster-whisper mirrors: - localai/localai-backends:master-nvidia-l4t-faster-whisper - name: moonshine-development alias: moonshine license: MIT description: | Moonshine is a fast, accurate, and efficient speech-to-text transcription model using ONNX Runtime. It provides real-time transcription capabilities with support for multiple model sizes and GPU acceleration. urls: - https://github.com/moonshine-ai/moonshine tags: - speech-to-text - transcription - ONNX capabilities: default: cpu-moonshine-development nvidia: cuda12-moonshine-development nvidia-cuda-12: cuda12-moonshine-development nvidia-cuda-13: cuda13-moonshine-development - name: cpu-moonshine alias: moonshine license: MIT description: | Moonshine is a fast, accurate, and efficient speech-to-text transcription model using ONNX Runtime. It provides real-time transcription capabilities with support for multiple model sizes and GPU acceleration. urls: - https://github.com/moonshine-ai/moonshine tags: - speech-to-text - transcription - ONNX capabilities: default: cpu-moonshine metal: metal-moonshine nvidia: cuda12-moonshine nvidia-cuda-12: cuda12-moonshine nvidia-cuda-13: cuda13-moonshine uri: quay.io/go-skynet/local-ai-backends:latest-cpu-moonshine mirrors: - localai/localai-backends:latest-cpu-moonshine - name: cpu-moonshine-development alias: moonshine license: MIT description: | Moonshine is a fast, accurate, and efficient speech-to-text transcription model using ONNX Runtime. It provides real-time transcription capabilities with support for multiple model sizes and GPU acceleration. urls: - https://github.com/moonshine-ai/moonshine tags: - speech-to-text - transcription - ONNX capabilities: default: cpu-moonshine metal: metal-moonshine nvidia: cuda12-moonshine nvidia-cuda-12: cuda12-moonshine nvidia-cuda-13: cuda13-moonshine uri: quay.io/go-skynet/local-ai-backends:master-cpu-moonshine mirrors: - localai/localai-backends:master-cpu-moonshine - name: cuda12-moonshine alias: moonshine license: MIT description: | Moonshine is a fast, accurate, and efficient speech-to-text transcription model using ONNX Runtime. It provides real-time transcription capabilities with support for multiple model sizes and GPU acceleration. urls: - https://github.com/moonshine-ai/moonshine tags: - speech-to-text - transcription - ONNX capabilities: default: cpu-moonshine metal: metal-moonshine nvidia: cuda12-moonshine nvidia-cuda-12: cuda12-moonshine nvidia-cuda-13: cuda13-moonshine uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-moonshine mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-moonshine - name: cuda12-moonshine-development alias: moonshine license: MIT description: | Moonshine is a fast, accurate, and efficient speech-to-text transcription model using ONNX Runtime. It provides real-time transcription capabilities with support for multiple model sizes and GPU acceleration. urls: - https://github.com/moonshine-ai/moonshine tags: - speech-to-text - transcription - ONNX capabilities: default: cpu-moonshine metal: metal-moonshine nvidia: cuda12-moonshine nvidia-cuda-12: cuda12-moonshine nvidia-cuda-13: cuda13-moonshine uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-moonshine mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-moonshine - name: cuda13-moonshine alias: moonshine license: MIT description: | Moonshine is a fast, accurate, and efficient speech-to-text transcription model using ONNX Runtime. It provides real-time transcription capabilities with support for multiple model sizes and GPU acceleration. urls: - https://github.com/moonshine-ai/moonshine tags: - speech-to-text - transcription - ONNX capabilities: default: cpu-moonshine metal: metal-moonshine nvidia: cuda12-moonshine nvidia-cuda-12: cuda12-moonshine nvidia-cuda-13: cuda13-moonshine uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-moonshine mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-moonshine - name: cuda13-moonshine-development alias: moonshine license: MIT description: | Moonshine is a fast, accurate, and efficient speech-to-text transcription model using ONNX Runtime. It provides real-time transcription capabilities with support for multiple model sizes and GPU acceleration. urls: - https://github.com/moonshine-ai/moonshine tags: - speech-to-text - transcription - ONNX capabilities: default: cpu-moonshine metal: metal-moonshine nvidia: cuda12-moonshine nvidia-cuda-12: cuda12-moonshine nvidia-cuda-13: cuda13-moonshine uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-moonshine mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-moonshine - name: metal-moonshine alias: moonshine license: MIT description: | Moonshine is a fast, accurate, and efficient speech-to-text transcription model using ONNX Runtime. It provides real-time transcription capabilities with support for multiple model sizes and GPU acceleration. urls: - https://github.com/moonshine-ai/moonshine tags: - speech-to-text - transcription - ONNX capabilities: default: cpu-moonshine metal: metal-moonshine nvidia: cuda12-moonshine nvidia-cuda-12: cuda12-moonshine nvidia-cuda-13: cuda13-moonshine uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-moonshine mirrors: - localai/localai-backends:latest-metal-darwin-arm64-moonshine - name: metal-moonshine-development alias: moonshine license: MIT description: | Moonshine is a fast, accurate, and efficient speech-to-text transcription model using ONNX Runtime. It provides real-time transcription capabilities with support for multiple model sizes and GPU acceleration. urls: - https://github.com/moonshine-ai/moonshine tags: - speech-to-text - transcription - ONNX capabilities: default: cpu-moonshine metal: metal-moonshine nvidia: cuda12-moonshine nvidia-cuda-12: cuda12-moonshine nvidia-cuda-13: cuda13-moonshine uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-moonshine mirrors: - localai/localai-backends:master-metal-darwin-arm64-moonshine - name: whisperx-development alias: whisperx license: BSD-4-Clause description: | WhisperX provides fast automatic speech recognition with word-level timestamps, speaker diarization, and forced alignment. Built on faster-whisper and pyannote-audio for high-accuracy transcription with speaker identification. urls: - https://github.com/m-bain/whisperX tags: - speech-to-text - diarization - whisperx capabilities: default: cpu-whisperx-development metal: metal-whisperx-development nvidia: cuda12-whisperx-development nvidia-cuda-12: cuda12-whisperx-development nvidia-cuda-13: cuda13-whisperx-development nvidia-l4t: nvidia-l4t-arm64-whisperx-development - name: cpu-whisperx alias: whisperx license: BSD-4-Clause description: | WhisperX provides fast automatic speech recognition with word-level timestamps, speaker diarization, and forced alignment. Built on faster-whisper and pyannote-audio for high-accuracy transcription with speaker identification. urls: - https://github.com/m-bain/whisperX tags: - speech-to-text - diarization - whisperx capabilities: default: cpu-whisperx metal: metal-whisperx nvidia: cuda12-whisperx nvidia-cuda-12: cuda12-whisperx nvidia-cuda-13: cuda13-whisperx nvidia-l4t: nvidia-l4t-arm64-whisperx nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisperx uri: quay.io/go-skynet/local-ai-backends:latest-cpu-whisperx mirrors: - localai/localai-backends:latest-cpu-whisperx - name: cpu-whisperx-development alias: whisperx license: BSD-4-Clause description: | WhisperX provides fast automatic speech recognition with word-level timestamps, speaker diarization, and forced alignment. Built on faster-whisper and pyannote-audio for high-accuracy transcription with speaker identification. urls: - https://github.com/m-bain/whisperX tags: - speech-to-text - diarization - whisperx capabilities: default: cpu-whisperx metal: metal-whisperx nvidia: cuda12-whisperx nvidia-cuda-12: cuda12-whisperx nvidia-cuda-13: cuda13-whisperx nvidia-l4t: nvidia-l4t-arm64-whisperx nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisperx uri: quay.io/go-skynet/local-ai-backends:master-cpu-whisperx mirrors: - localai/localai-backends:master-cpu-whisperx - name: cuda12-whisperx alias: whisperx license: BSD-4-Clause description: | WhisperX provides fast automatic speech recognition with word-level timestamps, speaker diarization, and forced alignment. Built on faster-whisper and pyannote-audio for high-accuracy transcription with speaker identification. urls: - https://github.com/m-bain/whisperX tags: - speech-to-text - diarization - whisperx capabilities: default: cpu-whisperx metal: metal-whisperx nvidia: cuda12-whisperx nvidia-cuda-12: cuda12-whisperx nvidia-cuda-13: cuda13-whisperx nvidia-l4t: nvidia-l4t-arm64-whisperx nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisperx uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-whisperx mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-whisperx - name: cuda12-whisperx-development alias: whisperx license: BSD-4-Clause description: | WhisperX provides fast automatic speech recognition with word-level timestamps, speaker diarization, and forced alignment. Built on faster-whisper and pyannote-audio for high-accuracy transcription with speaker identification. urls: - https://github.com/m-bain/whisperX tags: - speech-to-text - diarization - whisperx capabilities: default: cpu-whisperx metal: metal-whisperx nvidia: cuda12-whisperx nvidia-cuda-12: cuda12-whisperx nvidia-cuda-13: cuda13-whisperx nvidia-l4t: nvidia-l4t-arm64-whisperx nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisperx uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-whisperx mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-whisperx - name: cuda13-whisperx alias: whisperx license: BSD-4-Clause description: | WhisperX provides fast automatic speech recognition with word-level timestamps, speaker diarization, and forced alignment. Built on faster-whisper and pyannote-audio for high-accuracy transcription with speaker identification. urls: - https://github.com/m-bain/whisperX tags: - speech-to-text - diarization - whisperx capabilities: default: cpu-whisperx metal: metal-whisperx nvidia: cuda12-whisperx nvidia-cuda-12: cuda12-whisperx nvidia-cuda-13: cuda13-whisperx nvidia-l4t: nvidia-l4t-arm64-whisperx nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisperx uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-whisperx mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-whisperx - name: cuda13-whisperx-development alias: whisperx license: BSD-4-Clause description: | WhisperX provides fast automatic speech recognition with word-level timestamps, speaker diarization, and forced alignment. Built on faster-whisper and pyannote-audio for high-accuracy transcription with speaker identification. urls: - https://github.com/m-bain/whisperX tags: - speech-to-text - diarization - whisperx capabilities: default: cpu-whisperx metal: metal-whisperx nvidia: cuda12-whisperx nvidia-cuda-12: cuda12-whisperx nvidia-cuda-13: cuda13-whisperx nvidia-l4t: nvidia-l4t-arm64-whisperx nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisperx uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-whisperx mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-whisperx - name: metal-whisperx alias: whisperx license: BSD-4-Clause description: | WhisperX provides fast automatic speech recognition with word-level timestamps, speaker diarization, and forced alignment. Built on faster-whisper and pyannote-audio for high-accuracy transcription with speaker identification. urls: - https://github.com/m-bain/whisperX tags: - speech-to-text - diarization - whisperx capabilities: default: cpu-whisperx metal: metal-whisperx nvidia: cuda12-whisperx nvidia-cuda-12: cuda12-whisperx nvidia-cuda-13: cuda13-whisperx nvidia-l4t: nvidia-l4t-arm64-whisperx nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisperx uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-whisperx mirrors: - localai/localai-backends:latest-metal-darwin-arm64-whisperx - name: metal-whisperx-development alias: whisperx license: BSD-4-Clause description: | WhisperX provides fast automatic speech recognition with word-level timestamps, speaker diarization, and forced alignment. Built on faster-whisper and pyannote-audio for high-accuracy transcription with speaker identification. urls: - https://github.com/m-bain/whisperX tags: - speech-to-text - diarization - whisperx capabilities: default: cpu-whisperx metal: metal-whisperx nvidia: cuda12-whisperx nvidia-cuda-12: cuda12-whisperx nvidia-cuda-13: cuda13-whisperx nvidia-l4t: nvidia-l4t-arm64-whisperx nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisperx uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-whisperx mirrors: - localai/localai-backends:master-metal-darwin-arm64-whisperx - name: nvidia-l4t-arm64-whisperx alias: whisperx license: BSD-4-Clause description: | WhisperX provides fast automatic speech recognition with word-level timestamps, speaker diarization, and forced alignment. Built on faster-whisper and pyannote-audio for high-accuracy transcription with speaker identification. urls: - https://github.com/m-bain/whisperX tags: - speech-to-text - diarization - whisperx capabilities: default: cpu-whisperx metal: metal-whisperx nvidia: cuda12-whisperx nvidia-cuda-12: cuda12-whisperx nvidia-cuda-13: cuda13-whisperx nvidia-l4t: nvidia-l4t-arm64-whisperx nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisperx uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-whisperx mirrors: - localai/localai-backends:latest-nvidia-l4t-whisperx - name: nvidia-l4t-arm64-whisperx-development alias: whisperx license: BSD-4-Clause description: | WhisperX provides fast automatic speech recognition with word-level timestamps, speaker diarization, and forced alignment. Built on faster-whisper and pyannote-audio for high-accuracy transcription with speaker identification. urls: - https://github.com/m-bain/whisperX tags: - speech-to-text - diarization - whisperx capabilities: default: cpu-whisperx metal: metal-whisperx nvidia: cuda12-whisperx nvidia-cuda-12: cuda12-whisperx nvidia-cuda-13: cuda13-whisperx nvidia-l4t: nvidia-l4t-arm64-whisperx nvidia-l4t-cuda-12: nvidia-l4t-arm64-whisperx uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-whisperx mirrors: - localai/localai-backends:master-nvidia-l4t-whisperx - name: coqui-development alias: coqui license: mpl-2.0 icon: https://avatars.githubusercontent.com/u/1338804?s=200&v=4 description: "\U0001F438 Coqui TTS is a library for advanced Text-to-Speech generation.\n\n\U0001F680 Pretrained models in +1100 languages.\n\n\U0001F6E0️ Tools for training new models and fine-tuning existing models in any language.\n\n\U0001F4DA Utilities for dataset analysis and curation.\n" urls: - https://github.com/idiap/coqui-ai-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-coqui-development intel: intel-coqui-development metal: metal-coqui-development nvidia: cuda12-coqui-development - name: cuda12-coqui alias: coqui license: mpl-2.0 icon: https://avatars.githubusercontent.com/u/1338804?s=200&v=4 description: "\U0001F438 Coqui TTS is a library for advanced Text-to-Speech generation.\n\n\U0001F680 Pretrained models in +1100 languages.\n\n\U0001F6E0️ Tools for training new models and fine-tuning existing models in any language.\n\n\U0001F4DA Utilities for dataset analysis and curation.\n" urls: - https://github.com/idiap/coqui-ai-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-coqui intel: intel-coqui metal: metal-coqui nvidia: cuda12-coqui nvidia-cuda-12: cuda12-coqui uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-coqui mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-coqui - name: cuda12-coqui-development alias: coqui license: mpl-2.0 icon: https://avatars.githubusercontent.com/u/1338804?s=200&v=4 description: "\U0001F438 Coqui TTS is a library for advanced Text-to-Speech generation.\n\n\U0001F680 Pretrained models in +1100 languages.\n\n\U0001F6E0️ Tools for training new models and fine-tuning existing models in any language.\n\n\U0001F4DA Utilities for dataset analysis and curation.\n" urls: - https://github.com/idiap/coqui-ai-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-coqui intel: intel-coqui metal: metal-coqui nvidia: cuda12-coqui nvidia-cuda-12: cuda12-coqui uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-coqui mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-coqui - name: rocm-coqui-development alias: coqui license: mpl-2.0 icon: https://avatars.githubusercontent.com/u/1338804?s=200&v=4 description: "\U0001F438 Coqui TTS is a library for advanced Text-to-Speech generation.\n\n\U0001F680 Pretrained models in +1100 languages.\n\n\U0001F6E0️ Tools for training new models and fine-tuning existing models in any language.\n\n\U0001F4DA Utilities for dataset analysis and curation.\n" urls: - https://github.com/idiap/coqui-ai-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-coqui intel: intel-coqui metal: metal-coqui nvidia: cuda12-coqui nvidia-cuda-12: cuda12-coqui uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-coqui mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-coqui - name: intel-coqui alias: coqui license: mpl-2.0 icon: https://avatars.githubusercontent.com/u/1338804?s=200&v=4 description: "\U0001F438 Coqui TTS is a library for advanced Text-to-Speech generation.\n\n\U0001F680 Pretrained models in +1100 languages.\n\n\U0001F6E0️ Tools for training new models and fine-tuning existing models in any language.\n\n\U0001F4DA Utilities for dataset analysis and curation.\n" urls: - https://github.com/idiap/coqui-ai-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-coqui intel: intel-coqui metal: metal-coqui nvidia: cuda12-coqui nvidia-cuda-12: cuda12-coqui uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-coqui mirrors: - localai/localai-backends:latest-gpu-intel-coqui - name: intel-coqui-development alias: coqui license: mpl-2.0 icon: https://avatars.githubusercontent.com/u/1338804?s=200&v=4 description: "\U0001F438 Coqui TTS is a library for advanced Text-to-Speech generation.\n\n\U0001F680 Pretrained models in +1100 languages.\n\n\U0001F6E0️ Tools for training new models and fine-tuning existing models in any language.\n\n\U0001F4DA Utilities for dataset analysis and curation.\n" urls: - https://github.com/idiap/coqui-ai-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-coqui intel: intel-coqui metal: metal-coqui nvidia: cuda12-coqui nvidia-cuda-12: cuda12-coqui uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-coqui mirrors: - localai/localai-backends:master-gpu-intel-coqui - name: rocm-coqui alias: coqui license: mpl-2.0 icon: https://avatars.githubusercontent.com/u/1338804?s=200&v=4 description: "\U0001F438 Coqui TTS is a library for advanced Text-to-Speech generation.\n\n\U0001F680 Pretrained models in +1100 languages.\n\n\U0001F6E0️ Tools for training new models and fine-tuning existing models in any language.\n\n\U0001F4DA Utilities for dataset analysis and curation.\n" urls: - https://github.com/idiap/coqui-ai-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-coqui intel: intel-coqui metal: metal-coqui nvidia: cuda12-coqui nvidia-cuda-12: cuda12-coqui uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-coqui mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-coqui - name: metal-coqui alias: coqui license: mpl-2.0 icon: https://avatars.githubusercontent.com/u/1338804?s=200&v=4 description: "\U0001F438 Coqui TTS is a library for advanced Text-to-Speech generation.\n\n\U0001F680 Pretrained models in +1100 languages.\n\n\U0001F6E0️ Tools for training new models and fine-tuning existing models in any language.\n\n\U0001F4DA Utilities for dataset analysis and curation.\n" urls: - https://github.com/idiap/coqui-ai-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-coqui intel: intel-coqui metal: metal-coqui nvidia: cuda12-coqui nvidia-cuda-12: cuda12-coqui uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-coqui mirrors: - localai/localai-backends:latest-metal-darwin-arm64-coqui - name: metal-coqui-development alias: coqui license: mpl-2.0 icon: https://avatars.githubusercontent.com/u/1338804?s=200&v=4 description: "\U0001F438 Coqui TTS is a library for advanced Text-to-Speech generation.\n\n\U0001F680 Pretrained models in +1100 languages.\n\n\U0001F6E0️ Tools for training new models and fine-tuning existing models in any language.\n\n\U0001F4DA Utilities for dataset analysis and curation.\n" urls: - https://github.com/idiap/coqui-ai-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-coqui intel: intel-coqui metal: metal-coqui nvidia: cuda12-coqui nvidia-cuda-12: cuda12-coqui uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-coqui mirrors: - localai/localai-backends:master-metal-darwin-arm64-coqui - name: outetts-development alias: outetts license: apache-2.0 description: | OuteTTS is an open-weight text-to-speech model from OuteAI (OuteAI/OuteTTS-0.3-1B). Supports custom speaker voices via audio path or default speakers. urls: - https://github.com/OuteAI/outetts tags: - text-to-speech - TTS capabilities: default: cpu-outetts-development nvidia-cuda-12: cuda12-outetts-development - name: cpu-outetts alias: outetts license: apache-2.0 description: | OuteTTS is an open-weight text-to-speech model from OuteAI (OuteAI/OuteTTS-0.3-1B). Supports custom speaker voices via audio path or default speakers. urls: - https://github.com/OuteAI/outetts tags: - text-to-speech - TTS capabilities: default: cpu-outetts nvidia-cuda-12: cuda12-outetts uri: quay.io/go-skynet/local-ai-backends:latest-cpu-outetts mirrors: - localai/localai-backends:latest-cpu-outetts - name: cpu-outetts-development alias: outetts license: apache-2.0 description: | OuteTTS is an open-weight text-to-speech model from OuteAI (OuteAI/OuteTTS-0.3-1B). Supports custom speaker voices via audio path or default speakers. urls: - https://github.com/OuteAI/outetts tags: - text-to-speech - TTS capabilities: default: cpu-outetts nvidia-cuda-12: cuda12-outetts uri: quay.io/go-skynet/local-ai-backends:master-cpu-outetts mirrors: - localai/localai-backends:master-cpu-outetts - name: cuda12-outetts alias: outetts license: apache-2.0 description: | OuteTTS is an open-weight text-to-speech model from OuteAI (OuteAI/OuteTTS-0.3-1B). Supports custom speaker voices via audio path or default speakers. urls: - https://github.com/OuteAI/outetts tags: - text-to-speech - TTS capabilities: default: cpu-outetts nvidia-cuda-12: cuda12-outetts uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-outetts mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-outetts - name: cuda12-outetts-development alias: outetts license: apache-2.0 description: | OuteTTS is an open-weight text-to-speech model from OuteAI (OuteAI/OuteTTS-0.3-1B). Supports custom speaker voices via audio path or default speakers. urls: - https://github.com/OuteAI/outetts tags: - text-to-speech - TTS capabilities: default: cpu-outetts nvidia-cuda-12: cuda12-outetts uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-outetts mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-outetts - name: chatterbox-development alias: chatterbox license: MIT icon: https://avatars.githubusercontent.com/u/49844015?s=200&v=4 description: | Resemble AI's first production-grade open source TTS model. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs, and is consistently preferred in side-by-side evaluations. Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. It's also the first open source TTS model to support emotion exaggeration control, a powerful feature that makes your voices stand out. urls: - https://github.com/resemble-ai/chatterbox tags: - text-to-speech - TTS capabilities: default: cpu-chatterbox-development metal: metal-chatterbox-development nvidia: cuda12-chatterbox-development nvidia-cuda-12: cuda12-chatterbox-development nvidia-cuda-13: cuda13-chatterbox-development nvidia-l4t: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-12: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-chatterbox-development - name: cpu-chatterbox alias: chatterbox license: MIT icon: https://avatars.githubusercontent.com/u/49844015?s=200&v=4 description: | Resemble AI's first production-grade open source TTS model. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs, and is consistently preferred in side-by-side evaluations. Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. It's also the first open source TTS model to support emotion exaggeration control, a powerful feature that makes your voices stand out. urls: - https://github.com/resemble-ai/chatterbox tags: - text-to-speech - TTS capabilities: default: cpu-chatterbox metal: metal-chatterbox nvidia: cuda12-chatterbox nvidia-cuda-12: cuda12-chatterbox nvidia-cuda-13: cuda13-chatterbox nvidia-l4t: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-12: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-chatterbox uri: quay.io/go-skynet/local-ai-backends:latest-cpu-chatterbox mirrors: - localai/localai-backends:latest-cpu-chatterbox - name: cpu-chatterbox-development alias: chatterbox license: MIT icon: https://avatars.githubusercontent.com/u/49844015?s=200&v=4 description: | Resemble AI's first production-grade open source TTS model. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs, and is consistently preferred in side-by-side evaluations. Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. It's also the first open source TTS model to support emotion exaggeration control, a powerful feature that makes your voices stand out. urls: - https://github.com/resemble-ai/chatterbox tags: - text-to-speech - TTS capabilities: default: cpu-chatterbox metal: metal-chatterbox nvidia: cuda12-chatterbox nvidia-cuda-12: cuda12-chatterbox nvidia-cuda-13: cuda13-chatterbox nvidia-l4t: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-12: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-chatterbox uri: quay.io/go-skynet/local-ai-backends:master-cpu-chatterbox mirrors: - localai/localai-backends:master-cpu-chatterbox - name: nvidia-l4t-arm64-chatterbox alias: chatterbox license: MIT icon: https://avatars.githubusercontent.com/u/49844015?s=200&v=4 description: | Resemble AI's first production-grade open source TTS model. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs, and is consistently preferred in side-by-side evaluations. Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. It's also the first open source TTS model to support emotion exaggeration control, a powerful feature that makes your voices stand out. urls: - https://github.com/resemble-ai/chatterbox tags: - text-to-speech - TTS capabilities: default: cpu-chatterbox metal: metal-chatterbox nvidia: cuda12-chatterbox nvidia-cuda-12: cuda12-chatterbox nvidia-cuda-13: cuda13-chatterbox nvidia-l4t: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-12: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-chatterbox uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-chatterbox mirrors: - localai/localai-backends:latest-nvidia-l4t-arm64-chatterbox - name: nvidia-l4t-arm64-chatterbox-development alias: chatterbox license: MIT icon: https://avatars.githubusercontent.com/u/49844015?s=200&v=4 description: | Resemble AI's first production-grade open source TTS model. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs, and is consistently preferred in side-by-side evaluations. Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. It's also the first open source TTS model to support emotion exaggeration control, a powerful feature that makes your voices stand out. urls: - https://github.com/resemble-ai/chatterbox tags: - text-to-speech - TTS capabilities: default: cpu-chatterbox metal: metal-chatterbox nvidia: cuda12-chatterbox nvidia-cuda-12: cuda12-chatterbox nvidia-cuda-13: cuda13-chatterbox nvidia-l4t: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-12: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-chatterbox uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-chatterbox mirrors: - localai/localai-backends:master-nvidia-l4t-arm64-chatterbox - name: metal-chatterbox alias: chatterbox license: MIT icon: https://avatars.githubusercontent.com/u/49844015?s=200&v=4 description: | Resemble AI's first production-grade open source TTS model. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs, and is consistently preferred in side-by-side evaluations. Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. It's also the first open source TTS model to support emotion exaggeration control, a powerful feature that makes your voices stand out. urls: - https://github.com/resemble-ai/chatterbox tags: - text-to-speech - TTS capabilities: default: cpu-chatterbox metal: metal-chatterbox nvidia: cuda12-chatterbox nvidia-cuda-12: cuda12-chatterbox nvidia-cuda-13: cuda13-chatterbox nvidia-l4t: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-12: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-chatterbox uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-chatterbox mirrors: - localai/localai-backends:latest-metal-darwin-arm64-chatterbox - name: metal-chatterbox-development alias: chatterbox license: MIT icon: https://avatars.githubusercontent.com/u/49844015?s=200&v=4 description: | Resemble AI's first production-grade open source TTS model. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs, and is consistently preferred in side-by-side evaluations. Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. It's also the first open source TTS model to support emotion exaggeration control, a powerful feature that makes your voices stand out. urls: - https://github.com/resemble-ai/chatterbox tags: - text-to-speech - TTS capabilities: default: cpu-chatterbox metal: metal-chatterbox nvidia: cuda12-chatterbox nvidia-cuda-12: cuda12-chatterbox nvidia-cuda-13: cuda13-chatterbox nvidia-l4t: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-12: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-chatterbox uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-chatterbox mirrors: - localai/localai-backends:master-metal-darwin-arm64-chatterbox - name: cuda12-chatterbox-development alias: chatterbox license: MIT icon: https://avatars.githubusercontent.com/u/49844015?s=200&v=4 description: | Resemble AI's first production-grade open source TTS model. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs, and is consistently preferred in side-by-side evaluations. Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. It's also the first open source TTS model to support emotion exaggeration control, a powerful feature that makes your voices stand out. urls: - https://github.com/resemble-ai/chatterbox tags: - text-to-speech - TTS capabilities: default: cpu-chatterbox metal: metal-chatterbox nvidia: cuda12-chatterbox nvidia-cuda-12: cuda12-chatterbox nvidia-cuda-13: cuda13-chatterbox nvidia-l4t: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-12: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-chatterbox uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-chatterbox mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-chatterbox - name: cuda12-chatterbox alias: chatterbox license: MIT icon: https://avatars.githubusercontent.com/u/49844015?s=200&v=4 description: | Resemble AI's first production-grade open source TTS model. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs, and is consistently preferred in side-by-side evaluations. Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. It's also the first open source TTS model to support emotion exaggeration control, a powerful feature that makes your voices stand out. urls: - https://github.com/resemble-ai/chatterbox tags: - text-to-speech - TTS capabilities: default: cpu-chatterbox metal: metal-chatterbox nvidia: cuda12-chatterbox nvidia-cuda-12: cuda12-chatterbox nvidia-cuda-13: cuda13-chatterbox nvidia-l4t: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-12: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-chatterbox uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-chatterbox mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-chatterbox - name: cuda13-chatterbox alias: chatterbox license: MIT icon: https://avatars.githubusercontent.com/u/49844015?s=200&v=4 description: | Resemble AI's first production-grade open source TTS model. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs, and is consistently preferred in side-by-side evaluations. Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. It's also the first open source TTS model to support emotion exaggeration control, a powerful feature that makes your voices stand out. urls: - https://github.com/resemble-ai/chatterbox tags: - text-to-speech - TTS capabilities: default: cpu-chatterbox metal: metal-chatterbox nvidia: cuda12-chatterbox nvidia-cuda-12: cuda12-chatterbox nvidia-cuda-13: cuda13-chatterbox nvidia-l4t: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-12: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-chatterbox uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-chatterbox mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-chatterbox - name: cuda13-chatterbox-development alias: chatterbox license: MIT icon: https://avatars.githubusercontent.com/u/49844015?s=200&v=4 description: | Resemble AI's first production-grade open source TTS model. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs, and is consistently preferred in side-by-side evaluations. Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. It's also the first open source TTS model to support emotion exaggeration control, a powerful feature that makes your voices stand out. urls: - https://github.com/resemble-ai/chatterbox tags: - text-to-speech - TTS capabilities: default: cpu-chatterbox metal: metal-chatterbox nvidia: cuda12-chatterbox nvidia-cuda-12: cuda12-chatterbox nvidia-cuda-13: cuda13-chatterbox nvidia-l4t: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-12: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-chatterbox uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-chatterbox mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-chatterbox - name: cuda13-nvidia-l4t-arm64-chatterbox alias: chatterbox license: MIT icon: https://avatars.githubusercontent.com/u/49844015?s=200&v=4 description: | Resemble AI's first production-grade open source TTS model. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs, and is consistently preferred in side-by-side evaluations. Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. It's also the first open source TTS model to support emotion exaggeration control, a powerful feature that makes your voices stand out. urls: - https://github.com/resemble-ai/chatterbox tags: - text-to-speech - TTS capabilities: default: cpu-chatterbox metal: metal-chatterbox nvidia: cuda12-chatterbox nvidia-cuda-12: cuda12-chatterbox nvidia-cuda-13: cuda13-chatterbox nvidia-l4t: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-12: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-chatterbox uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-chatterbox mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-chatterbox - name: cuda13-nvidia-l4t-arm64-chatterbox-development alias: chatterbox license: MIT icon: https://avatars.githubusercontent.com/u/49844015?s=200&v=4 description: | Resemble AI's first production-grade open source TTS model. Licensed under MIT, Chatterbox has been benchmarked against leading closed-source systems like ElevenLabs, and is consistently preferred in side-by-side evaluations. Whether you're working on memes, videos, games, or AI agents, Chatterbox brings your content to life. It's also the first open source TTS model to support emotion exaggeration control, a powerful feature that makes your voices stand out. urls: - https://github.com/resemble-ai/chatterbox tags: - text-to-speech - TTS capabilities: default: cpu-chatterbox metal: metal-chatterbox nvidia: cuda12-chatterbox nvidia-cuda-12: cuda12-chatterbox nvidia-cuda-13: cuda13-chatterbox nvidia-l4t: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-12: nvidia-l4t-arm64-chatterbox nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-chatterbox uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-chatterbox mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-chatterbox - name: vibevoice-development alias: vibevoice license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VibeVoice-Realtime is a real-time text-to-speech model that generates natural-sounding speech. urls: - https://github.com/microsoft/VibeVoice tags: - text-to-speech - TTS capabilities: amd: rocm-vibevoice-development default: cpu-vibevoice-development intel: intel-vibevoice-development metal: metal-vibevoice-development nvidia: cuda12-vibevoice-development nvidia-cuda-12: cuda12-vibevoice-development nvidia-cuda-13: cuda13-vibevoice-development nvidia-l4t: nvidia-l4t-vibevoice-development nvidia-l4t-cuda-12: nvidia-l4t-vibevoice-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice-development - name: cpu-vibevoice alias: vibevoice license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VibeVoice-Realtime is a real-time text-to-speech model that generates natural-sounding speech. urls: - https://github.com/microsoft/VibeVoice tags: - text-to-speech - TTS capabilities: amd: rocm-vibevoice default: cpu-vibevoice intel: intel-vibevoice metal: metal-vibevoice nvidia: cuda12-vibevoice nvidia-cuda-12: cuda12-vibevoice nvidia-cuda-13: cuda13-vibevoice nvidia-l4t: nvidia-l4t-vibevoice nvidia-l4t-cuda-12: nvidia-l4t-vibevoice nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice uri: quay.io/go-skynet/local-ai-backends:latest-cpu-vibevoice mirrors: - localai/localai-backends:latest-cpu-vibevoice - name: cpu-vibevoice-development alias: vibevoice license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VibeVoice-Realtime is a real-time text-to-speech model that generates natural-sounding speech. urls: - https://github.com/microsoft/VibeVoice tags: - text-to-speech - TTS capabilities: amd: rocm-vibevoice default: cpu-vibevoice intel: intel-vibevoice metal: metal-vibevoice nvidia: cuda12-vibevoice nvidia-cuda-12: cuda12-vibevoice nvidia-cuda-13: cuda13-vibevoice nvidia-l4t: nvidia-l4t-vibevoice nvidia-l4t-cuda-12: nvidia-l4t-vibevoice nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice uri: quay.io/go-skynet/local-ai-backends:master-cpu-vibevoice mirrors: - localai/localai-backends:master-cpu-vibevoice - name: cuda12-vibevoice alias: vibevoice license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VibeVoice-Realtime is a real-time text-to-speech model that generates natural-sounding speech. urls: - https://github.com/microsoft/VibeVoice tags: - text-to-speech - TTS capabilities: amd: rocm-vibevoice default: cpu-vibevoice intel: intel-vibevoice metal: metal-vibevoice nvidia: cuda12-vibevoice nvidia-cuda-12: cuda12-vibevoice nvidia-cuda-13: cuda13-vibevoice nvidia-l4t: nvidia-l4t-vibevoice nvidia-l4t-cuda-12: nvidia-l4t-vibevoice nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-vibevoice mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-vibevoice - name: cuda12-vibevoice-development alias: vibevoice license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VibeVoice-Realtime is a real-time text-to-speech model that generates natural-sounding speech. urls: - https://github.com/microsoft/VibeVoice tags: - text-to-speech - TTS capabilities: amd: rocm-vibevoice default: cpu-vibevoice intel: intel-vibevoice metal: metal-vibevoice nvidia: cuda12-vibevoice nvidia-cuda-12: cuda12-vibevoice nvidia-cuda-13: cuda13-vibevoice nvidia-l4t: nvidia-l4t-vibevoice nvidia-l4t-cuda-12: nvidia-l4t-vibevoice nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-vibevoice mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-vibevoice - name: cuda13-vibevoice alias: vibevoice license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VibeVoice-Realtime is a real-time text-to-speech model that generates natural-sounding speech. urls: - https://github.com/microsoft/VibeVoice tags: - text-to-speech - TTS capabilities: amd: rocm-vibevoice default: cpu-vibevoice intel: intel-vibevoice metal: metal-vibevoice nvidia: cuda12-vibevoice nvidia-cuda-12: cuda12-vibevoice nvidia-cuda-13: cuda13-vibevoice nvidia-l4t: nvidia-l4t-vibevoice nvidia-l4t-cuda-12: nvidia-l4t-vibevoice nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-vibevoice mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-vibevoice - name: cuda13-vibevoice-development alias: vibevoice license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VibeVoice-Realtime is a real-time text-to-speech model that generates natural-sounding speech. urls: - https://github.com/microsoft/VibeVoice tags: - text-to-speech - TTS capabilities: amd: rocm-vibevoice default: cpu-vibevoice intel: intel-vibevoice metal: metal-vibevoice nvidia: cuda12-vibevoice nvidia-cuda-12: cuda12-vibevoice nvidia-cuda-13: cuda13-vibevoice nvidia-l4t: nvidia-l4t-vibevoice nvidia-l4t-cuda-12: nvidia-l4t-vibevoice nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-vibevoice mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-vibevoice - name: intel-vibevoice alias: vibevoice license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VibeVoice-Realtime is a real-time text-to-speech model that generates natural-sounding speech. urls: - https://github.com/microsoft/VibeVoice tags: - text-to-speech - TTS capabilities: amd: rocm-vibevoice default: cpu-vibevoice intel: intel-vibevoice metal: metal-vibevoice nvidia: cuda12-vibevoice nvidia-cuda-12: cuda12-vibevoice nvidia-cuda-13: cuda13-vibevoice nvidia-l4t: nvidia-l4t-vibevoice nvidia-l4t-cuda-12: nvidia-l4t-vibevoice nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-vibevoice mirrors: - localai/localai-backends:latest-gpu-intel-vibevoice - name: intel-vibevoice-development alias: vibevoice license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VibeVoice-Realtime is a real-time text-to-speech model that generates natural-sounding speech. urls: - https://github.com/microsoft/VibeVoice tags: - text-to-speech - TTS capabilities: amd: rocm-vibevoice default: cpu-vibevoice intel: intel-vibevoice metal: metal-vibevoice nvidia: cuda12-vibevoice nvidia-cuda-12: cuda12-vibevoice nvidia-cuda-13: cuda13-vibevoice nvidia-l4t: nvidia-l4t-vibevoice nvidia-l4t-cuda-12: nvidia-l4t-vibevoice nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-vibevoice mirrors: - localai/localai-backends:master-gpu-intel-vibevoice - name: rocm-vibevoice alias: vibevoice license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VibeVoice-Realtime is a real-time text-to-speech model that generates natural-sounding speech. urls: - https://github.com/microsoft/VibeVoice tags: - text-to-speech - TTS capabilities: amd: rocm-vibevoice default: cpu-vibevoice intel: intel-vibevoice metal: metal-vibevoice nvidia: cuda12-vibevoice nvidia-cuda-12: cuda12-vibevoice nvidia-cuda-13: cuda13-vibevoice nvidia-l4t: nvidia-l4t-vibevoice nvidia-l4t-cuda-12: nvidia-l4t-vibevoice nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-vibevoice mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-vibevoice - name: rocm-vibevoice-development alias: vibevoice license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VibeVoice-Realtime is a real-time text-to-speech model that generates natural-sounding speech. urls: - https://github.com/microsoft/VibeVoice tags: - text-to-speech - TTS capabilities: amd: rocm-vibevoice default: cpu-vibevoice intel: intel-vibevoice metal: metal-vibevoice nvidia: cuda12-vibevoice nvidia-cuda-12: cuda12-vibevoice nvidia-cuda-13: cuda13-vibevoice nvidia-l4t: nvidia-l4t-vibevoice nvidia-l4t-cuda-12: nvidia-l4t-vibevoice nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-vibevoice mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-vibevoice - name: nvidia-l4t-vibevoice alias: vibevoice license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VibeVoice-Realtime is a real-time text-to-speech model that generates natural-sounding speech. urls: - https://github.com/microsoft/VibeVoice tags: - text-to-speech - TTS capabilities: amd: rocm-vibevoice default: cpu-vibevoice intel: intel-vibevoice metal: metal-vibevoice nvidia: cuda12-vibevoice nvidia-cuda-12: cuda12-vibevoice nvidia-cuda-13: cuda13-vibevoice nvidia-l4t: nvidia-l4t-vibevoice nvidia-l4t-cuda-12: nvidia-l4t-vibevoice nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-vibevoice mirrors: - localai/localai-backends:latest-nvidia-l4t-vibevoice - name: nvidia-l4t-vibevoice-development alias: vibevoice license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VibeVoice-Realtime is a real-time text-to-speech model that generates natural-sounding speech. urls: - https://github.com/microsoft/VibeVoice tags: - text-to-speech - TTS capabilities: amd: rocm-vibevoice default: cpu-vibevoice intel: intel-vibevoice metal: metal-vibevoice nvidia: cuda12-vibevoice nvidia-cuda-12: cuda12-vibevoice nvidia-cuda-13: cuda13-vibevoice nvidia-l4t: nvidia-l4t-vibevoice nvidia-l4t-cuda-12: nvidia-l4t-vibevoice nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-vibevoice mirrors: - localai/localai-backends:master-nvidia-l4t-vibevoice - name: cuda13-nvidia-l4t-arm64-vibevoice alias: vibevoice license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VibeVoice-Realtime is a real-time text-to-speech model that generates natural-sounding speech. urls: - https://github.com/microsoft/VibeVoice tags: - text-to-speech - TTS capabilities: amd: rocm-vibevoice default: cpu-vibevoice intel: intel-vibevoice metal: metal-vibevoice nvidia: cuda12-vibevoice nvidia-cuda-12: cuda12-vibevoice nvidia-cuda-13: cuda13-vibevoice nvidia-l4t: nvidia-l4t-vibevoice nvidia-l4t-cuda-12: nvidia-l4t-vibevoice nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-vibevoice mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-vibevoice - name: cuda13-nvidia-l4t-arm64-vibevoice-development alias: vibevoice license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VibeVoice-Realtime is a real-time text-to-speech model that generates natural-sounding speech. urls: - https://github.com/microsoft/VibeVoice tags: - text-to-speech - TTS capabilities: amd: rocm-vibevoice default: cpu-vibevoice intel: intel-vibevoice metal: metal-vibevoice nvidia: cuda12-vibevoice nvidia-cuda-12: cuda12-vibevoice nvidia-cuda-13: cuda13-vibevoice nvidia-l4t: nvidia-l4t-vibevoice nvidia-l4t-cuda-12: nvidia-l4t-vibevoice nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-vibevoice mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-vibevoice - name: metal-vibevoice alias: vibevoice license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VibeVoice-Realtime is a real-time text-to-speech model that generates natural-sounding speech. urls: - https://github.com/microsoft/VibeVoice tags: - text-to-speech - TTS capabilities: amd: rocm-vibevoice default: cpu-vibevoice intel: intel-vibevoice metal: metal-vibevoice nvidia: cuda12-vibevoice nvidia-cuda-12: cuda12-vibevoice nvidia-cuda-13: cuda13-vibevoice nvidia-l4t: nvidia-l4t-vibevoice nvidia-l4t-cuda-12: nvidia-l4t-vibevoice nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-vibevoice mirrors: - localai/localai-backends:latest-metal-darwin-arm64-vibevoice - name: metal-vibevoice-development alias: vibevoice license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VibeVoice-Realtime is a real-time text-to-speech model that generates natural-sounding speech. urls: - https://github.com/microsoft/VibeVoice tags: - text-to-speech - TTS capabilities: amd: rocm-vibevoice default: cpu-vibevoice intel: intel-vibevoice metal: metal-vibevoice nvidia: cuda12-vibevoice nvidia-cuda-12: cuda12-vibevoice nvidia-cuda-13: cuda13-vibevoice nvidia-l4t: nvidia-l4t-vibevoice nvidia-l4t-cuda-12: nvidia-l4t-vibevoice nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-vibevoice uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-vibevoice mirrors: - localai/localai-backends:master-metal-darwin-arm64-vibevoice - name: qwen-tts-development alias: qwen-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-TTS is a high-quality text-to-speech model supporting custom voice, voice design, and voice cloning. urls: - https://github.com/QwenLM/Qwen3-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-qwen-tts-development default: cpu-qwen-tts-development intel: intel-qwen-tts-development metal: metal-qwen-tts-development nvidia: cuda12-qwen-tts-development nvidia-cuda-12: cuda12-qwen-tts-development nvidia-cuda-13: cuda13-qwen-tts-development nvidia-l4t: nvidia-l4t-qwen-tts-development nvidia-l4t-cuda-12: nvidia-l4t-qwen-tts-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-tts-development - name: cpu-qwen-tts alias: qwen-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-TTS is a high-quality text-to-speech model supporting custom voice, voice design, and voice cloning. urls: - https://github.com/QwenLM/Qwen3-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-qwen-tts default: cpu-qwen-tts intel: intel-qwen-tts metal: metal-qwen-tts nvidia: cuda12-qwen-tts nvidia-cuda-12: cuda12-qwen-tts nvidia-cuda-13: cuda13-qwen-tts nvidia-l4t: nvidia-l4t-qwen-tts nvidia-l4t-cuda-12: nvidia-l4t-qwen-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-tts uri: quay.io/go-skynet/local-ai-backends:latest-cpu-qwen-tts mirrors: - localai/localai-backends:latest-cpu-qwen-tts - name: cpu-qwen-tts-development alias: qwen-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-TTS is a high-quality text-to-speech model supporting custom voice, voice design, and voice cloning. urls: - https://github.com/QwenLM/Qwen3-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-qwen-tts default: cpu-qwen-tts intel: intel-qwen-tts metal: metal-qwen-tts nvidia: cuda12-qwen-tts nvidia-cuda-12: cuda12-qwen-tts nvidia-cuda-13: cuda13-qwen-tts nvidia-l4t: nvidia-l4t-qwen-tts nvidia-l4t-cuda-12: nvidia-l4t-qwen-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-tts uri: quay.io/go-skynet/local-ai-backends:master-cpu-qwen-tts mirrors: - localai/localai-backends:master-cpu-qwen-tts - name: cuda12-qwen-tts alias: qwen-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-TTS is a high-quality text-to-speech model supporting custom voice, voice design, and voice cloning. urls: - https://github.com/QwenLM/Qwen3-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-qwen-tts default: cpu-qwen-tts intel: intel-qwen-tts metal: metal-qwen-tts nvidia: cuda12-qwen-tts nvidia-cuda-12: cuda12-qwen-tts nvidia-cuda-13: cuda13-qwen-tts nvidia-l4t: nvidia-l4t-qwen-tts nvidia-l4t-cuda-12: nvidia-l4t-qwen-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-tts uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-qwen-tts mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-qwen-tts - name: cuda12-qwen-tts-development alias: qwen-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-TTS is a high-quality text-to-speech model supporting custom voice, voice design, and voice cloning. urls: - https://github.com/QwenLM/Qwen3-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-qwen-tts default: cpu-qwen-tts intel: intel-qwen-tts metal: metal-qwen-tts nvidia: cuda12-qwen-tts nvidia-cuda-12: cuda12-qwen-tts nvidia-cuda-13: cuda13-qwen-tts nvidia-l4t: nvidia-l4t-qwen-tts nvidia-l4t-cuda-12: nvidia-l4t-qwen-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-tts uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-qwen-tts mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-qwen-tts - name: cuda13-qwen-tts alias: qwen-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-TTS is a high-quality text-to-speech model supporting custom voice, voice design, and voice cloning. urls: - https://github.com/QwenLM/Qwen3-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-qwen-tts default: cpu-qwen-tts intel: intel-qwen-tts metal: metal-qwen-tts nvidia: cuda12-qwen-tts nvidia-cuda-12: cuda12-qwen-tts nvidia-cuda-13: cuda13-qwen-tts nvidia-l4t: nvidia-l4t-qwen-tts nvidia-l4t-cuda-12: nvidia-l4t-qwen-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-tts uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-qwen-tts mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-qwen-tts - name: cuda13-qwen-tts-development alias: qwen-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-TTS is a high-quality text-to-speech model supporting custom voice, voice design, and voice cloning. urls: - https://github.com/QwenLM/Qwen3-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-qwen-tts default: cpu-qwen-tts intel: intel-qwen-tts metal: metal-qwen-tts nvidia: cuda12-qwen-tts nvidia-cuda-12: cuda12-qwen-tts nvidia-cuda-13: cuda13-qwen-tts nvidia-l4t: nvidia-l4t-qwen-tts nvidia-l4t-cuda-12: nvidia-l4t-qwen-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-tts uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-qwen-tts mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-qwen-tts - name: intel-qwen-tts alias: qwen-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-TTS is a high-quality text-to-speech model supporting custom voice, voice design, and voice cloning. urls: - https://github.com/QwenLM/Qwen3-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-qwen-tts default: cpu-qwen-tts intel: intel-qwen-tts metal: metal-qwen-tts nvidia: cuda12-qwen-tts nvidia-cuda-12: cuda12-qwen-tts nvidia-cuda-13: cuda13-qwen-tts nvidia-l4t: nvidia-l4t-qwen-tts nvidia-l4t-cuda-12: nvidia-l4t-qwen-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-tts uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-qwen-tts mirrors: - localai/localai-backends:latest-gpu-intel-qwen-tts - name: intel-qwen-tts-development alias: qwen-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-TTS is a high-quality text-to-speech model supporting custom voice, voice design, and voice cloning. urls: - https://github.com/QwenLM/Qwen3-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-qwen-tts default: cpu-qwen-tts intel: intel-qwen-tts metal: metal-qwen-tts nvidia: cuda12-qwen-tts nvidia-cuda-12: cuda12-qwen-tts nvidia-cuda-13: cuda13-qwen-tts nvidia-l4t: nvidia-l4t-qwen-tts nvidia-l4t-cuda-12: nvidia-l4t-qwen-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-tts uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-qwen-tts mirrors: - localai/localai-backends:master-gpu-intel-qwen-tts - name: rocm-qwen-tts alias: qwen-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-TTS is a high-quality text-to-speech model supporting custom voice, voice design, and voice cloning. urls: - https://github.com/QwenLM/Qwen3-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-qwen-tts default: cpu-qwen-tts intel: intel-qwen-tts metal: metal-qwen-tts nvidia: cuda12-qwen-tts nvidia-cuda-12: cuda12-qwen-tts nvidia-cuda-13: cuda13-qwen-tts nvidia-l4t: nvidia-l4t-qwen-tts nvidia-l4t-cuda-12: nvidia-l4t-qwen-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-tts uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-qwen-tts mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-qwen-tts - name: rocm-qwen-tts-development alias: qwen-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-TTS is a high-quality text-to-speech model supporting custom voice, voice design, and voice cloning. urls: - https://github.com/QwenLM/Qwen3-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-qwen-tts default: cpu-qwen-tts intel: intel-qwen-tts metal: metal-qwen-tts nvidia: cuda12-qwen-tts nvidia-cuda-12: cuda12-qwen-tts nvidia-cuda-13: cuda13-qwen-tts nvidia-l4t: nvidia-l4t-qwen-tts nvidia-l4t-cuda-12: nvidia-l4t-qwen-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-tts uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-qwen-tts mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-qwen-tts - name: nvidia-l4t-qwen-tts alias: qwen-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-TTS is a high-quality text-to-speech model supporting custom voice, voice design, and voice cloning. urls: - https://github.com/QwenLM/Qwen3-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-qwen-tts default: cpu-qwen-tts intel: intel-qwen-tts metal: metal-qwen-tts nvidia: cuda12-qwen-tts nvidia-cuda-12: cuda12-qwen-tts nvidia-cuda-13: cuda13-qwen-tts nvidia-l4t: nvidia-l4t-qwen-tts nvidia-l4t-cuda-12: nvidia-l4t-qwen-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-tts uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-qwen-tts mirrors: - localai/localai-backends:latest-nvidia-l4t-qwen-tts - name: nvidia-l4t-qwen-tts-development alias: qwen-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-TTS is a high-quality text-to-speech model supporting custom voice, voice design, and voice cloning. urls: - https://github.com/QwenLM/Qwen3-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-qwen-tts default: cpu-qwen-tts intel: intel-qwen-tts metal: metal-qwen-tts nvidia: cuda12-qwen-tts nvidia-cuda-12: cuda12-qwen-tts nvidia-cuda-13: cuda13-qwen-tts nvidia-l4t: nvidia-l4t-qwen-tts nvidia-l4t-cuda-12: nvidia-l4t-qwen-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-tts uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-qwen-tts mirrors: - localai/localai-backends:master-nvidia-l4t-qwen-tts - name: cuda13-nvidia-l4t-arm64-qwen-tts alias: qwen-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-TTS is a high-quality text-to-speech model supporting custom voice, voice design, and voice cloning. urls: - https://github.com/QwenLM/Qwen3-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-qwen-tts default: cpu-qwen-tts intel: intel-qwen-tts metal: metal-qwen-tts nvidia: cuda12-qwen-tts nvidia-cuda-12: cuda12-qwen-tts nvidia-cuda-13: cuda13-qwen-tts nvidia-l4t: nvidia-l4t-qwen-tts nvidia-l4t-cuda-12: nvidia-l4t-qwen-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-tts uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-qwen-tts mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-qwen-tts - name: cuda13-nvidia-l4t-arm64-qwen-tts-development alias: qwen-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-TTS is a high-quality text-to-speech model supporting custom voice, voice design, and voice cloning. urls: - https://github.com/QwenLM/Qwen3-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-qwen-tts default: cpu-qwen-tts intel: intel-qwen-tts metal: metal-qwen-tts nvidia: cuda12-qwen-tts nvidia-cuda-12: cuda12-qwen-tts nvidia-cuda-13: cuda13-qwen-tts nvidia-l4t: nvidia-l4t-qwen-tts nvidia-l4t-cuda-12: nvidia-l4t-qwen-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-tts uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-qwen-tts mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-qwen-tts - name: metal-qwen-tts alias: qwen-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-TTS is a high-quality text-to-speech model supporting custom voice, voice design, and voice cloning. urls: - https://github.com/QwenLM/Qwen3-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-qwen-tts default: cpu-qwen-tts intel: intel-qwen-tts metal: metal-qwen-tts nvidia: cuda12-qwen-tts nvidia-cuda-12: cuda12-qwen-tts nvidia-cuda-13: cuda13-qwen-tts nvidia-l4t: nvidia-l4t-qwen-tts nvidia-l4t-cuda-12: nvidia-l4t-qwen-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-tts uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-qwen-tts mirrors: - localai/localai-backends:latest-metal-darwin-arm64-qwen-tts - name: metal-qwen-tts-development alias: qwen-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-TTS is a high-quality text-to-speech model supporting custom voice, voice design, and voice cloning. urls: - https://github.com/QwenLM/Qwen3-TTS tags: - text-to-speech - TTS capabilities: amd: rocm-qwen-tts default: cpu-qwen-tts intel: intel-qwen-tts metal: metal-qwen-tts nvidia: cuda12-qwen-tts nvidia-cuda-12: cuda12-qwen-tts nvidia-cuda-13: cuda13-qwen-tts nvidia-l4t: nvidia-l4t-qwen-tts nvidia-l4t-cuda-12: nvidia-l4t-qwen-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-tts uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-qwen-tts mirrors: - localai/localai-backends:master-metal-darwin-arm64-qwen-tts - name: fish-speech-development alias: fish-speech license: apache-2.0 icon: https://avatars.githubusercontent.com/u/148526220?s=200&v=4 description: | Fish Speech is a high-quality text-to-speech model supporting voice cloning via reference audio. urls: - https://github.com/fishaudio/fish-speech tags: - text-to-speech - TTS - voice-cloning capabilities: amd: rocm-fish-speech-development default: cpu-fish-speech-development intel: intel-fish-speech-development nvidia: cuda12-fish-speech-development nvidia-cuda-12: cuda12-fish-speech-development nvidia-cuda-13: cuda13-fish-speech-development nvidia-l4t: nvidia-l4t-fish-speech-development nvidia-l4t-cuda-12: nvidia-l4t-fish-speech-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-fish-speech-development - name: cpu-fish-speech alias: fish-speech license: apache-2.0 icon: https://avatars.githubusercontent.com/u/148526220?s=200&v=4 description: | Fish Speech is a high-quality text-to-speech model supporting voice cloning via reference audio. urls: - https://github.com/fishaudio/fish-speech tags: - text-to-speech - TTS - voice-cloning capabilities: amd: rocm-fish-speech default: cpu-fish-speech intel: intel-fish-speech nvidia: cuda12-fish-speech nvidia-cuda-12: cuda12-fish-speech nvidia-cuda-13: cuda13-fish-speech nvidia-l4t: nvidia-l4t-fish-speech nvidia-l4t-cuda-12: nvidia-l4t-fish-speech nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-fish-speech uri: quay.io/go-skynet/local-ai-backends:latest-cpu-fish-speech mirrors: - localai/localai-backends:latest-cpu-fish-speech - name: cpu-fish-speech-development alias: fish-speech license: apache-2.0 icon: https://avatars.githubusercontent.com/u/148526220?s=200&v=4 description: | Fish Speech is a high-quality text-to-speech model supporting voice cloning via reference audio. urls: - https://github.com/fishaudio/fish-speech tags: - text-to-speech - TTS - voice-cloning capabilities: amd: rocm-fish-speech default: cpu-fish-speech intel: intel-fish-speech nvidia: cuda12-fish-speech nvidia-cuda-12: cuda12-fish-speech nvidia-cuda-13: cuda13-fish-speech nvidia-l4t: nvidia-l4t-fish-speech nvidia-l4t-cuda-12: nvidia-l4t-fish-speech nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-fish-speech uri: quay.io/go-skynet/local-ai-backends:master-cpu-fish-speech mirrors: - localai/localai-backends:master-cpu-fish-speech - name: cuda12-fish-speech alias: fish-speech license: apache-2.0 icon: https://avatars.githubusercontent.com/u/148526220?s=200&v=4 description: | Fish Speech is a high-quality text-to-speech model supporting voice cloning via reference audio. urls: - https://github.com/fishaudio/fish-speech tags: - text-to-speech - TTS - voice-cloning capabilities: amd: rocm-fish-speech default: cpu-fish-speech intel: intel-fish-speech nvidia: cuda12-fish-speech nvidia-cuda-12: cuda12-fish-speech nvidia-cuda-13: cuda13-fish-speech nvidia-l4t: nvidia-l4t-fish-speech nvidia-l4t-cuda-12: nvidia-l4t-fish-speech nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-fish-speech uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-fish-speech mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-fish-speech - name: cuda12-fish-speech-development alias: fish-speech license: apache-2.0 icon: https://avatars.githubusercontent.com/u/148526220?s=200&v=4 description: | Fish Speech is a high-quality text-to-speech model supporting voice cloning via reference audio. urls: - https://github.com/fishaudio/fish-speech tags: - text-to-speech - TTS - voice-cloning capabilities: amd: rocm-fish-speech default: cpu-fish-speech intel: intel-fish-speech nvidia: cuda12-fish-speech nvidia-cuda-12: cuda12-fish-speech nvidia-cuda-13: cuda13-fish-speech nvidia-l4t: nvidia-l4t-fish-speech nvidia-l4t-cuda-12: nvidia-l4t-fish-speech nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-fish-speech uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-fish-speech mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-fish-speech - name: cuda13-fish-speech alias: fish-speech license: apache-2.0 icon: https://avatars.githubusercontent.com/u/148526220?s=200&v=4 description: | Fish Speech is a high-quality text-to-speech model supporting voice cloning via reference audio. urls: - https://github.com/fishaudio/fish-speech tags: - text-to-speech - TTS - voice-cloning capabilities: amd: rocm-fish-speech default: cpu-fish-speech intel: intel-fish-speech nvidia: cuda12-fish-speech nvidia-cuda-12: cuda12-fish-speech nvidia-cuda-13: cuda13-fish-speech nvidia-l4t: nvidia-l4t-fish-speech nvidia-l4t-cuda-12: nvidia-l4t-fish-speech nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-fish-speech uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-fish-speech mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-fish-speech - name: cuda13-fish-speech-development alias: fish-speech license: apache-2.0 icon: https://avatars.githubusercontent.com/u/148526220?s=200&v=4 description: | Fish Speech is a high-quality text-to-speech model supporting voice cloning via reference audio. urls: - https://github.com/fishaudio/fish-speech tags: - text-to-speech - TTS - voice-cloning capabilities: amd: rocm-fish-speech default: cpu-fish-speech intel: intel-fish-speech nvidia: cuda12-fish-speech nvidia-cuda-12: cuda12-fish-speech nvidia-cuda-13: cuda13-fish-speech nvidia-l4t: nvidia-l4t-fish-speech nvidia-l4t-cuda-12: nvidia-l4t-fish-speech nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-fish-speech uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-fish-speech mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-fish-speech - name: intel-fish-speech alias: fish-speech license: apache-2.0 icon: https://avatars.githubusercontent.com/u/148526220?s=200&v=4 description: | Fish Speech is a high-quality text-to-speech model supporting voice cloning via reference audio. urls: - https://github.com/fishaudio/fish-speech tags: - text-to-speech - TTS - voice-cloning capabilities: amd: rocm-fish-speech default: cpu-fish-speech intel: intel-fish-speech nvidia: cuda12-fish-speech nvidia-cuda-12: cuda12-fish-speech nvidia-cuda-13: cuda13-fish-speech nvidia-l4t: nvidia-l4t-fish-speech nvidia-l4t-cuda-12: nvidia-l4t-fish-speech nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-fish-speech uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-fish-speech mirrors: - localai/localai-backends:latest-gpu-intel-fish-speech - name: intel-fish-speech-development alias: fish-speech license: apache-2.0 icon: https://avatars.githubusercontent.com/u/148526220?s=200&v=4 description: | Fish Speech is a high-quality text-to-speech model supporting voice cloning via reference audio. urls: - https://github.com/fishaudio/fish-speech tags: - text-to-speech - TTS - voice-cloning capabilities: amd: rocm-fish-speech default: cpu-fish-speech intel: intel-fish-speech nvidia: cuda12-fish-speech nvidia-cuda-12: cuda12-fish-speech nvidia-cuda-13: cuda13-fish-speech nvidia-l4t: nvidia-l4t-fish-speech nvidia-l4t-cuda-12: nvidia-l4t-fish-speech nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-fish-speech uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-fish-speech mirrors: - localai/localai-backends:master-gpu-intel-fish-speech - name: rocm-fish-speech alias: fish-speech license: apache-2.0 icon: https://avatars.githubusercontent.com/u/148526220?s=200&v=4 description: | Fish Speech is a high-quality text-to-speech model supporting voice cloning via reference audio. urls: - https://github.com/fishaudio/fish-speech tags: - text-to-speech - TTS - voice-cloning capabilities: amd: rocm-fish-speech default: cpu-fish-speech intel: intel-fish-speech nvidia: cuda12-fish-speech nvidia-cuda-12: cuda12-fish-speech nvidia-cuda-13: cuda13-fish-speech nvidia-l4t: nvidia-l4t-fish-speech nvidia-l4t-cuda-12: nvidia-l4t-fish-speech nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-fish-speech uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-fish-speech mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-fish-speech - name: rocm-fish-speech-development alias: fish-speech license: apache-2.0 icon: https://avatars.githubusercontent.com/u/148526220?s=200&v=4 description: | Fish Speech is a high-quality text-to-speech model supporting voice cloning via reference audio. urls: - https://github.com/fishaudio/fish-speech tags: - text-to-speech - TTS - voice-cloning capabilities: amd: rocm-fish-speech default: cpu-fish-speech intel: intel-fish-speech nvidia: cuda12-fish-speech nvidia-cuda-12: cuda12-fish-speech nvidia-cuda-13: cuda13-fish-speech nvidia-l4t: nvidia-l4t-fish-speech nvidia-l4t-cuda-12: nvidia-l4t-fish-speech nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-fish-speech uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-fish-speech mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-fish-speech - name: nvidia-l4t-fish-speech alias: fish-speech license: apache-2.0 icon: https://avatars.githubusercontent.com/u/148526220?s=200&v=4 description: | Fish Speech is a high-quality text-to-speech model supporting voice cloning via reference audio. urls: - https://github.com/fishaudio/fish-speech tags: - text-to-speech - TTS - voice-cloning capabilities: amd: rocm-fish-speech default: cpu-fish-speech intel: intel-fish-speech nvidia: cuda12-fish-speech nvidia-cuda-12: cuda12-fish-speech nvidia-cuda-13: cuda13-fish-speech nvidia-l4t: nvidia-l4t-fish-speech nvidia-l4t-cuda-12: nvidia-l4t-fish-speech nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-fish-speech uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-fish-speech mirrors: - localai/localai-backends:latest-nvidia-l4t-fish-speech - name: nvidia-l4t-fish-speech-development alias: fish-speech license: apache-2.0 icon: https://avatars.githubusercontent.com/u/148526220?s=200&v=4 description: | Fish Speech is a high-quality text-to-speech model supporting voice cloning via reference audio. urls: - https://github.com/fishaudio/fish-speech tags: - text-to-speech - TTS - voice-cloning capabilities: amd: rocm-fish-speech default: cpu-fish-speech intel: intel-fish-speech nvidia: cuda12-fish-speech nvidia-cuda-12: cuda12-fish-speech nvidia-cuda-13: cuda13-fish-speech nvidia-l4t: nvidia-l4t-fish-speech nvidia-l4t-cuda-12: nvidia-l4t-fish-speech nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-fish-speech uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-fish-speech mirrors: - localai/localai-backends:master-nvidia-l4t-fish-speech - name: cuda13-nvidia-l4t-arm64-fish-speech alias: fish-speech license: apache-2.0 icon: https://avatars.githubusercontent.com/u/148526220?s=200&v=4 description: | Fish Speech is a high-quality text-to-speech model supporting voice cloning via reference audio. urls: - https://github.com/fishaudio/fish-speech tags: - text-to-speech - TTS - voice-cloning capabilities: amd: rocm-fish-speech default: cpu-fish-speech intel: intel-fish-speech nvidia: cuda12-fish-speech nvidia-cuda-12: cuda12-fish-speech nvidia-cuda-13: cuda13-fish-speech nvidia-l4t: nvidia-l4t-fish-speech nvidia-l4t-cuda-12: nvidia-l4t-fish-speech nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-fish-speech uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-fish-speech mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-fish-speech - name: cuda13-nvidia-l4t-arm64-fish-speech-development alias: fish-speech license: apache-2.0 icon: https://avatars.githubusercontent.com/u/148526220?s=200&v=4 description: | Fish Speech is a high-quality text-to-speech model supporting voice cloning via reference audio. urls: - https://github.com/fishaudio/fish-speech tags: - text-to-speech - TTS - voice-cloning capabilities: amd: rocm-fish-speech default: cpu-fish-speech intel: intel-fish-speech nvidia: cuda12-fish-speech nvidia-cuda-12: cuda12-fish-speech nvidia-cuda-13: cuda13-fish-speech nvidia-l4t: nvidia-l4t-fish-speech nvidia-l4t-cuda-12: nvidia-l4t-fish-speech nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-fish-speech uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-fish-speech mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-fish-speech - name: faster-qwen3-tts-development alias: faster-qwen3-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Real-time Qwen3-TTS inference using CUDA graph capture. Voice clone only; requires NVIDIA GPU with CUDA. urls: - https://github.com/andimarafioti/faster-qwen3-tts - https://pypi.org/project/faster-qwen3-tts/ tags: - text-to-speech - TTS - voice-clone capabilities: default: cuda12-faster-qwen3-tts-development nvidia: cuda12-faster-qwen3-tts-development nvidia-cuda-12: cuda12-faster-qwen3-tts-development nvidia-cuda-13: cuda13-faster-qwen3-tts-development nvidia-l4t: nvidia-l4t-faster-qwen3-tts-development nvidia-l4t-cuda-12: nvidia-l4t-faster-qwen3-tts-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-faster-qwen3-tts-development - name: cuda12-faster-qwen3-tts alias: faster-qwen3-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Real-time Qwen3-TTS inference using CUDA graph capture. Voice clone only; requires NVIDIA GPU with CUDA. urls: - https://github.com/andimarafioti/faster-qwen3-tts - https://pypi.org/project/faster-qwen3-tts/ tags: - text-to-speech - TTS - voice-clone capabilities: default: cuda12-faster-qwen3-tts nvidia: cuda12-faster-qwen3-tts nvidia-cuda-12: cuda12-faster-qwen3-tts nvidia-cuda-13: cuda13-faster-qwen3-tts nvidia-l4t: nvidia-l4t-faster-qwen3-tts nvidia-l4t-cuda-12: nvidia-l4t-faster-qwen3-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-faster-qwen3-tts uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-faster-qwen3-tts mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-faster-qwen3-tts - name: cuda12-faster-qwen3-tts-development alias: faster-qwen3-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Real-time Qwen3-TTS inference using CUDA graph capture. Voice clone only; requires NVIDIA GPU with CUDA. urls: - https://github.com/andimarafioti/faster-qwen3-tts - https://pypi.org/project/faster-qwen3-tts/ tags: - text-to-speech - TTS - voice-clone capabilities: default: cuda12-faster-qwen3-tts nvidia: cuda12-faster-qwen3-tts nvidia-cuda-12: cuda12-faster-qwen3-tts nvidia-cuda-13: cuda13-faster-qwen3-tts nvidia-l4t: nvidia-l4t-faster-qwen3-tts nvidia-l4t-cuda-12: nvidia-l4t-faster-qwen3-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-faster-qwen3-tts uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-faster-qwen3-tts mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-faster-qwen3-tts - name: cuda13-faster-qwen3-tts alias: faster-qwen3-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Real-time Qwen3-TTS inference using CUDA graph capture. Voice clone only; requires NVIDIA GPU with CUDA. urls: - https://github.com/andimarafioti/faster-qwen3-tts - https://pypi.org/project/faster-qwen3-tts/ tags: - text-to-speech - TTS - voice-clone capabilities: default: cuda12-faster-qwen3-tts nvidia: cuda12-faster-qwen3-tts nvidia-cuda-12: cuda12-faster-qwen3-tts nvidia-cuda-13: cuda13-faster-qwen3-tts nvidia-l4t: nvidia-l4t-faster-qwen3-tts nvidia-l4t-cuda-12: nvidia-l4t-faster-qwen3-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-faster-qwen3-tts uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-faster-qwen3-tts mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-faster-qwen3-tts - name: cuda13-faster-qwen3-tts-development alias: faster-qwen3-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Real-time Qwen3-TTS inference using CUDA graph capture. Voice clone only; requires NVIDIA GPU with CUDA. urls: - https://github.com/andimarafioti/faster-qwen3-tts - https://pypi.org/project/faster-qwen3-tts/ tags: - text-to-speech - TTS - voice-clone capabilities: default: cuda12-faster-qwen3-tts nvidia: cuda12-faster-qwen3-tts nvidia-cuda-12: cuda12-faster-qwen3-tts nvidia-cuda-13: cuda13-faster-qwen3-tts nvidia-l4t: nvidia-l4t-faster-qwen3-tts nvidia-l4t-cuda-12: nvidia-l4t-faster-qwen3-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-faster-qwen3-tts uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-faster-qwen3-tts mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-faster-qwen3-tts - name: nvidia-l4t-faster-qwen3-tts alias: faster-qwen3-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Real-time Qwen3-TTS inference using CUDA graph capture. Voice clone only; requires NVIDIA GPU with CUDA. urls: - https://github.com/andimarafioti/faster-qwen3-tts - https://pypi.org/project/faster-qwen3-tts/ tags: - text-to-speech - TTS - voice-clone capabilities: default: cuda12-faster-qwen3-tts nvidia: cuda12-faster-qwen3-tts nvidia-cuda-12: cuda12-faster-qwen3-tts nvidia-cuda-13: cuda13-faster-qwen3-tts nvidia-l4t: nvidia-l4t-faster-qwen3-tts nvidia-l4t-cuda-12: nvidia-l4t-faster-qwen3-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-faster-qwen3-tts uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-faster-qwen3-tts mirrors: - localai/localai-backends:latest-nvidia-l4t-faster-qwen3-tts - name: nvidia-l4t-faster-qwen3-tts-development alias: faster-qwen3-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Real-time Qwen3-TTS inference using CUDA graph capture. Voice clone only; requires NVIDIA GPU with CUDA. urls: - https://github.com/andimarafioti/faster-qwen3-tts - https://pypi.org/project/faster-qwen3-tts/ tags: - text-to-speech - TTS - voice-clone capabilities: default: cuda12-faster-qwen3-tts nvidia: cuda12-faster-qwen3-tts nvidia-cuda-12: cuda12-faster-qwen3-tts nvidia-cuda-13: cuda13-faster-qwen3-tts nvidia-l4t: nvidia-l4t-faster-qwen3-tts nvidia-l4t-cuda-12: nvidia-l4t-faster-qwen3-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-faster-qwen3-tts uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-faster-qwen3-tts mirrors: - localai/localai-backends:master-nvidia-l4t-faster-qwen3-tts - name: cuda13-nvidia-l4t-arm64-faster-qwen3-tts alias: faster-qwen3-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Real-time Qwen3-TTS inference using CUDA graph capture. Voice clone only; requires NVIDIA GPU with CUDA. urls: - https://github.com/andimarafioti/faster-qwen3-tts - https://pypi.org/project/faster-qwen3-tts/ tags: - text-to-speech - TTS - voice-clone capabilities: default: cuda12-faster-qwen3-tts nvidia: cuda12-faster-qwen3-tts nvidia-cuda-12: cuda12-faster-qwen3-tts nvidia-cuda-13: cuda13-faster-qwen3-tts nvidia-l4t: nvidia-l4t-faster-qwen3-tts nvidia-l4t-cuda-12: nvidia-l4t-faster-qwen3-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-faster-qwen3-tts uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-faster-qwen3-tts mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-faster-qwen3-tts - name: cuda13-nvidia-l4t-arm64-faster-qwen3-tts-development alias: faster-qwen3-tts license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Real-time Qwen3-TTS inference using CUDA graph capture. Voice clone only; requires NVIDIA GPU with CUDA. urls: - https://github.com/andimarafioti/faster-qwen3-tts - https://pypi.org/project/faster-qwen3-tts/ tags: - text-to-speech - TTS - voice-clone capabilities: default: cuda12-faster-qwen3-tts nvidia: cuda12-faster-qwen3-tts nvidia-cuda-12: cuda12-faster-qwen3-tts nvidia-cuda-13: cuda13-faster-qwen3-tts nvidia-l4t: nvidia-l4t-faster-qwen3-tts nvidia-l4t-cuda-12: nvidia-l4t-faster-qwen3-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-faster-qwen3-tts uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-faster-qwen3-tts mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-faster-qwen3-tts - name: whisper-medusa-development alias: whisper-medusa license: MIT description: | Whisper-Medusa accelerates Whisper transcription by predicting multiple tokens per decoding step. The upstream checkpoints use custom Transformers generation code and accept audio clips up to 30 seconds. urls: - https://github.com/aiola-lab/whisper-medusa - https://huggingface.co/collections/aiola/whisper-medusa tags: - speech-to-text - transcription - Whisper - Medusa capabilities: default: cpu-whisper-medusa-development nvidia: cuda12-whisper-medusa-development nvidia-cuda-12: cuda12-whisper-medusa-development - name: cpu-whisper-medusa alias: whisper-medusa license: MIT description: | Whisper-Medusa accelerates Whisper transcription by predicting multiple tokens per decoding step. The upstream checkpoints use custom Transformers generation code and accept audio clips up to 30 seconds. urls: - https://github.com/aiola-lab/whisper-medusa - https://huggingface.co/collections/aiola/whisper-medusa tags: - speech-to-text - transcription - Whisper - Medusa capabilities: default: cpu-whisper-medusa nvidia: cuda12-whisper-medusa nvidia-cuda-12: cuda12-whisper-medusa uri: quay.io/go-skynet/local-ai-backends:latest-cpu-whisper-medusa mirrors: - localai/localai-backends:latest-cpu-whisper-medusa - name: cpu-whisper-medusa-development alias: whisper-medusa license: MIT description: | Whisper-Medusa accelerates Whisper transcription by predicting multiple tokens per decoding step. The upstream checkpoints use custom Transformers generation code and accept audio clips up to 30 seconds. urls: - https://github.com/aiola-lab/whisper-medusa - https://huggingface.co/collections/aiola/whisper-medusa tags: - speech-to-text - transcription - Whisper - Medusa capabilities: default: cpu-whisper-medusa nvidia: cuda12-whisper-medusa nvidia-cuda-12: cuda12-whisper-medusa uri: quay.io/go-skynet/local-ai-backends:master-cpu-whisper-medusa mirrors: - localai/localai-backends:master-cpu-whisper-medusa - name: cuda12-whisper-medusa alias: whisper-medusa license: MIT description: | Whisper-Medusa accelerates Whisper transcription by predicting multiple tokens per decoding step. The upstream checkpoints use custom Transformers generation code and accept audio clips up to 30 seconds. urls: - https://github.com/aiola-lab/whisper-medusa - https://huggingface.co/collections/aiola/whisper-medusa tags: - speech-to-text - transcription - Whisper - Medusa capabilities: default: cpu-whisper-medusa nvidia: cuda12-whisper-medusa nvidia-cuda-12: cuda12-whisper-medusa uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-whisper-medusa mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-whisper-medusa - name: cuda12-whisper-medusa-development alias: whisper-medusa license: MIT description: | Whisper-Medusa accelerates Whisper transcription by predicting multiple tokens per decoding step. The upstream checkpoints use custom Transformers generation code and accept audio clips up to 30 seconds. urls: - https://github.com/aiola-lab/whisper-medusa - https://huggingface.co/collections/aiola/whisper-medusa tags: - speech-to-text - transcription - Whisper - Medusa capabilities: default: cpu-whisper-medusa nvidia: cuda12-whisper-medusa nvidia-cuda-12: cuda12-whisper-medusa uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-whisper-medusa mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-whisper-medusa - name: qwen-asr-development alias: qwen-asr license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-ASR is an automatic speech recognition model supporting multiple languages and batch inference. urls: - https://github.com/QwenLM/Qwen3-ASR tags: - speech-recognition - ASR capabilities: amd: rocm-qwen-asr-development default: cpu-qwen-asr-development intel: intel-qwen-asr-development metal: metal-qwen-asr-development nvidia: cuda12-qwen-asr-development nvidia-cuda-12: cuda12-qwen-asr-development nvidia-cuda-13: cuda13-qwen-asr-development nvidia-l4t: nvidia-l4t-qwen-asr-development nvidia-l4t-cuda-12: nvidia-l4t-qwen-asr-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-asr-development - name: cpu-qwen-asr alias: qwen-asr license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-ASR is an automatic speech recognition model supporting multiple languages and batch inference. urls: - https://github.com/QwenLM/Qwen3-ASR tags: - speech-recognition - ASR capabilities: amd: rocm-qwen-asr default: cpu-qwen-asr intel: intel-qwen-asr metal: metal-qwen-asr nvidia: cuda12-qwen-asr nvidia-cuda-12: cuda12-qwen-asr nvidia-cuda-13: cuda13-qwen-asr nvidia-l4t: nvidia-l4t-qwen-asr nvidia-l4t-cuda-12: nvidia-l4t-qwen-asr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-asr uri: quay.io/go-skynet/local-ai-backends:latest-cpu-qwen-asr mirrors: - localai/localai-backends:latest-cpu-qwen-asr - name: cpu-qwen-asr-development alias: qwen-asr license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-ASR is an automatic speech recognition model supporting multiple languages and batch inference. urls: - https://github.com/QwenLM/Qwen3-ASR tags: - speech-recognition - ASR capabilities: amd: rocm-qwen-asr default: cpu-qwen-asr intel: intel-qwen-asr metal: metal-qwen-asr nvidia: cuda12-qwen-asr nvidia-cuda-12: cuda12-qwen-asr nvidia-cuda-13: cuda13-qwen-asr nvidia-l4t: nvidia-l4t-qwen-asr nvidia-l4t-cuda-12: nvidia-l4t-qwen-asr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-asr uri: quay.io/go-skynet/local-ai-backends:master-cpu-qwen-asr mirrors: - localai/localai-backends:master-cpu-qwen-asr - name: cuda12-qwen-asr alias: qwen-asr license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-ASR is an automatic speech recognition model supporting multiple languages and batch inference. urls: - https://github.com/QwenLM/Qwen3-ASR tags: - speech-recognition - ASR capabilities: amd: rocm-qwen-asr default: cpu-qwen-asr intel: intel-qwen-asr metal: metal-qwen-asr nvidia: cuda12-qwen-asr nvidia-cuda-12: cuda12-qwen-asr nvidia-cuda-13: cuda13-qwen-asr nvidia-l4t: nvidia-l4t-qwen-asr nvidia-l4t-cuda-12: nvidia-l4t-qwen-asr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-asr uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-qwen-asr mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-qwen-asr - name: cuda12-qwen-asr-development alias: qwen-asr license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-ASR is an automatic speech recognition model supporting multiple languages and batch inference. urls: - https://github.com/QwenLM/Qwen3-ASR tags: - speech-recognition - ASR capabilities: amd: rocm-qwen-asr default: cpu-qwen-asr intel: intel-qwen-asr metal: metal-qwen-asr nvidia: cuda12-qwen-asr nvidia-cuda-12: cuda12-qwen-asr nvidia-cuda-13: cuda13-qwen-asr nvidia-l4t: nvidia-l4t-qwen-asr nvidia-l4t-cuda-12: nvidia-l4t-qwen-asr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-asr uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-qwen-asr mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-qwen-asr - name: cuda13-qwen-asr alias: qwen-asr license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-ASR is an automatic speech recognition model supporting multiple languages and batch inference. urls: - https://github.com/QwenLM/Qwen3-ASR tags: - speech-recognition - ASR capabilities: amd: rocm-qwen-asr default: cpu-qwen-asr intel: intel-qwen-asr metal: metal-qwen-asr nvidia: cuda12-qwen-asr nvidia-cuda-12: cuda12-qwen-asr nvidia-cuda-13: cuda13-qwen-asr nvidia-l4t: nvidia-l4t-qwen-asr nvidia-l4t-cuda-12: nvidia-l4t-qwen-asr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-asr uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-qwen-asr mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-qwen-asr - name: cuda13-qwen-asr-development alias: qwen-asr license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-ASR is an automatic speech recognition model supporting multiple languages and batch inference. urls: - https://github.com/QwenLM/Qwen3-ASR tags: - speech-recognition - ASR capabilities: amd: rocm-qwen-asr default: cpu-qwen-asr intel: intel-qwen-asr metal: metal-qwen-asr nvidia: cuda12-qwen-asr nvidia-cuda-12: cuda12-qwen-asr nvidia-cuda-13: cuda13-qwen-asr nvidia-l4t: nvidia-l4t-qwen-asr nvidia-l4t-cuda-12: nvidia-l4t-qwen-asr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-asr uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-qwen-asr mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-qwen-asr - name: intel-qwen-asr alias: qwen-asr license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-ASR is an automatic speech recognition model supporting multiple languages and batch inference. urls: - https://github.com/QwenLM/Qwen3-ASR tags: - speech-recognition - ASR capabilities: amd: rocm-qwen-asr default: cpu-qwen-asr intel: intel-qwen-asr metal: metal-qwen-asr nvidia: cuda12-qwen-asr nvidia-cuda-12: cuda12-qwen-asr nvidia-cuda-13: cuda13-qwen-asr nvidia-l4t: nvidia-l4t-qwen-asr nvidia-l4t-cuda-12: nvidia-l4t-qwen-asr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-asr uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-qwen-asr mirrors: - localai/localai-backends:latest-gpu-intel-qwen-asr - name: intel-qwen-asr-development alias: qwen-asr license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-ASR is an automatic speech recognition model supporting multiple languages and batch inference. urls: - https://github.com/QwenLM/Qwen3-ASR tags: - speech-recognition - ASR capabilities: amd: rocm-qwen-asr default: cpu-qwen-asr intel: intel-qwen-asr metal: metal-qwen-asr nvidia: cuda12-qwen-asr nvidia-cuda-12: cuda12-qwen-asr nvidia-cuda-13: cuda13-qwen-asr nvidia-l4t: nvidia-l4t-qwen-asr nvidia-l4t-cuda-12: nvidia-l4t-qwen-asr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-asr uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-qwen-asr mirrors: - localai/localai-backends:master-gpu-intel-qwen-asr - name: rocm-qwen-asr alias: qwen-asr license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-ASR is an automatic speech recognition model supporting multiple languages and batch inference. urls: - https://github.com/QwenLM/Qwen3-ASR tags: - speech-recognition - ASR capabilities: amd: rocm-qwen-asr default: cpu-qwen-asr intel: intel-qwen-asr metal: metal-qwen-asr nvidia: cuda12-qwen-asr nvidia-cuda-12: cuda12-qwen-asr nvidia-cuda-13: cuda13-qwen-asr nvidia-l4t: nvidia-l4t-qwen-asr nvidia-l4t-cuda-12: nvidia-l4t-qwen-asr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-asr uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-qwen-asr mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-qwen-asr - name: rocm-qwen-asr-development alias: qwen-asr license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-ASR is an automatic speech recognition model supporting multiple languages and batch inference. urls: - https://github.com/QwenLM/Qwen3-ASR tags: - speech-recognition - ASR capabilities: amd: rocm-qwen-asr default: cpu-qwen-asr intel: intel-qwen-asr metal: metal-qwen-asr nvidia: cuda12-qwen-asr nvidia-cuda-12: cuda12-qwen-asr nvidia-cuda-13: cuda13-qwen-asr nvidia-l4t: nvidia-l4t-qwen-asr nvidia-l4t-cuda-12: nvidia-l4t-qwen-asr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-asr uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-qwen-asr mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-qwen-asr - name: nvidia-l4t-qwen-asr alias: qwen-asr license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-ASR is an automatic speech recognition model supporting multiple languages and batch inference. urls: - https://github.com/QwenLM/Qwen3-ASR tags: - speech-recognition - ASR capabilities: amd: rocm-qwen-asr default: cpu-qwen-asr intel: intel-qwen-asr metal: metal-qwen-asr nvidia: cuda12-qwen-asr nvidia-cuda-12: cuda12-qwen-asr nvidia-cuda-13: cuda13-qwen-asr nvidia-l4t: nvidia-l4t-qwen-asr nvidia-l4t-cuda-12: nvidia-l4t-qwen-asr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-asr uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-qwen-asr mirrors: - localai/localai-backends:latest-nvidia-l4t-qwen-asr - name: nvidia-l4t-qwen-asr-development alias: qwen-asr license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-ASR is an automatic speech recognition model supporting multiple languages and batch inference. urls: - https://github.com/QwenLM/Qwen3-ASR tags: - speech-recognition - ASR capabilities: amd: rocm-qwen-asr default: cpu-qwen-asr intel: intel-qwen-asr metal: metal-qwen-asr nvidia: cuda12-qwen-asr nvidia-cuda-12: cuda12-qwen-asr nvidia-cuda-13: cuda13-qwen-asr nvidia-l4t: nvidia-l4t-qwen-asr nvidia-l4t-cuda-12: nvidia-l4t-qwen-asr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-asr uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-qwen-asr mirrors: - localai/localai-backends:master-nvidia-l4t-qwen-asr - name: cuda13-nvidia-l4t-arm64-qwen-asr alias: qwen-asr license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-ASR is an automatic speech recognition model supporting multiple languages and batch inference. urls: - https://github.com/QwenLM/Qwen3-ASR tags: - speech-recognition - ASR capabilities: amd: rocm-qwen-asr default: cpu-qwen-asr intel: intel-qwen-asr metal: metal-qwen-asr nvidia: cuda12-qwen-asr nvidia-cuda-12: cuda12-qwen-asr nvidia-cuda-13: cuda13-qwen-asr nvidia-l4t: nvidia-l4t-qwen-asr nvidia-l4t-cuda-12: nvidia-l4t-qwen-asr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-asr uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-qwen-asr mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-qwen-asr - name: cuda13-nvidia-l4t-arm64-qwen-asr-development alias: qwen-asr license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-ASR is an automatic speech recognition model supporting multiple languages and batch inference. urls: - https://github.com/QwenLM/Qwen3-ASR tags: - speech-recognition - ASR capabilities: amd: rocm-qwen-asr default: cpu-qwen-asr intel: intel-qwen-asr metal: metal-qwen-asr nvidia: cuda12-qwen-asr nvidia-cuda-12: cuda12-qwen-asr nvidia-cuda-13: cuda13-qwen-asr nvidia-l4t: nvidia-l4t-qwen-asr nvidia-l4t-cuda-12: nvidia-l4t-qwen-asr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-asr uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-qwen-asr mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-qwen-asr - name: metal-qwen-asr alias: qwen-asr license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-ASR is an automatic speech recognition model supporting multiple languages and batch inference. urls: - https://github.com/QwenLM/Qwen3-ASR tags: - speech-recognition - ASR capabilities: amd: rocm-qwen-asr default: cpu-qwen-asr intel: intel-qwen-asr metal: metal-qwen-asr nvidia: cuda12-qwen-asr nvidia-cuda-12: cuda12-qwen-asr nvidia-cuda-13: cuda13-qwen-asr nvidia-l4t: nvidia-l4t-qwen-asr nvidia-l4t-cuda-12: nvidia-l4t-qwen-asr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-asr uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-qwen-asr mirrors: - localai/localai-backends:latest-metal-darwin-arm64-qwen-asr - name: metal-qwen-asr-development alias: qwen-asr license: apache-2.0 icon: https://cdn-avatars.huggingface.co/v1/production/uploads/620760a26e3b7210c2ff1943/-s1gyJfvbE1RgO5iBeNOi.png description: | Qwen3-ASR is an automatic speech recognition model supporting multiple languages and batch inference. urls: - https://github.com/QwenLM/Qwen3-ASR tags: - speech-recognition - ASR capabilities: amd: rocm-qwen-asr default: cpu-qwen-asr intel: intel-qwen-asr metal: metal-qwen-asr nvidia: cuda12-qwen-asr nvidia-cuda-12: cuda12-qwen-asr nvidia-cuda-13: cuda13-qwen-asr nvidia-l4t: nvidia-l4t-qwen-asr nvidia-l4t-cuda-12: nvidia-l4t-qwen-asr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-qwen-asr uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-qwen-asr mirrors: - localai/localai-backends:master-metal-darwin-arm64-qwen-asr - name: nemo-development alias: nemo license: apache-2.0 icon: https://www.nvidia.com/favicon.ico description: | NVIDIA NEMO Toolkit for ASR provides state-of-the-art automatic speech recognition models including Parakeet models for various languages and use cases. urls: - https://github.com/NVIDIA/NeMo tags: - speech-recognition - ASR - NVIDIA capabilities: amd: rocm-nemo-development default: cpu-nemo-development intel: intel-nemo-development metal: metal-nemo-development nvidia: cuda12-nemo-development nvidia-cuda-12: cuda12-nemo-development nvidia-cuda-13: cuda13-nemo-development - name: cpu-nemo alias: nemo license: apache-2.0 icon: https://www.nvidia.com/favicon.ico description: | NVIDIA NEMO Toolkit for ASR provides state-of-the-art automatic speech recognition models including Parakeet models for various languages and use cases. urls: - https://github.com/NVIDIA/NeMo tags: - speech-recognition - ASR - NVIDIA capabilities: amd: rocm-nemo default: cpu-nemo intel: intel-nemo metal: metal-nemo nvidia: cuda12-nemo nvidia-cuda-12: cuda12-nemo nvidia-cuda-13: cuda13-nemo uri: quay.io/go-skynet/local-ai-backends:latest-cpu-nemo mirrors: - localai/localai-backends:latest-cpu-nemo - name: cpu-nemo-development alias: nemo license: apache-2.0 icon: https://www.nvidia.com/favicon.ico description: | NVIDIA NEMO Toolkit for ASR provides state-of-the-art automatic speech recognition models including Parakeet models for various languages and use cases. urls: - https://github.com/NVIDIA/NeMo tags: - speech-recognition - ASR - NVIDIA capabilities: amd: rocm-nemo default: cpu-nemo intel: intel-nemo metal: metal-nemo nvidia: cuda12-nemo nvidia-cuda-12: cuda12-nemo nvidia-cuda-13: cuda13-nemo uri: quay.io/go-skynet/local-ai-backends:master-cpu-nemo mirrors: - localai/localai-backends:master-cpu-nemo - name: cuda12-nemo alias: nemo license: apache-2.0 icon: https://www.nvidia.com/favicon.ico description: | NVIDIA NEMO Toolkit for ASR provides state-of-the-art automatic speech recognition models including Parakeet models for various languages and use cases. urls: - https://github.com/NVIDIA/NeMo tags: - speech-recognition - ASR - NVIDIA capabilities: amd: rocm-nemo default: cpu-nemo intel: intel-nemo metal: metal-nemo nvidia: cuda12-nemo nvidia-cuda-12: cuda12-nemo nvidia-cuda-13: cuda13-nemo uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-nemo mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-nemo - name: cuda12-nemo-development alias: nemo license: apache-2.0 icon: https://www.nvidia.com/favicon.ico description: | NVIDIA NEMO Toolkit for ASR provides state-of-the-art automatic speech recognition models including Parakeet models for various languages and use cases. urls: - https://github.com/NVIDIA/NeMo tags: - speech-recognition - ASR - NVIDIA capabilities: amd: rocm-nemo default: cpu-nemo intel: intel-nemo metal: metal-nemo nvidia: cuda12-nemo nvidia-cuda-12: cuda12-nemo nvidia-cuda-13: cuda13-nemo uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-nemo mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-nemo - name: cuda13-nemo alias: nemo license: apache-2.0 icon: https://www.nvidia.com/favicon.ico description: | NVIDIA NEMO Toolkit for ASR provides state-of-the-art automatic speech recognition models including Parakeet models for various languages and use cases. urls: - https://github.com/NVIDIA/NeMo tags: - speech-recognition - ASR - NVIDIA capabilities: amd: rocm-nemo default: cpu-nemo intel: intel-nemo metal: metal-nemo nvidia: cuda12-nemo nvidia-cuda-12: cuda12-nemo nvidia-cuda-13: cuda13-nemo uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-nemo mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-nemo - name: cuda13-nemo-development alias: nemo license: apache-2.0 icon: https://www.nvidia.com/favicon.ico description: | NVIDIA NEMO Toolkit for ASR provides state-of-the-art automatic speech recognition models including Parakeet models for various languages and use cases. urls: - https://github.com/NVIDIA/NeMo tags: - speech-recognition - ASR - NVIDIA capabilities: amd: rocm-nemo default: cpu-nemo intel: intel-nemo metal: metal-nemo nvidia: cuda12-nemo nvidia-cuda-12: cuda12-nemo nvidia-cuda-13: cuda13-nemo uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-nemo mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-nemo - name: intel-nemo alias: nemo license: apache-2.0 icon: https://www.nvidia.com/favicon.ico description: | NVIDIA NEMO Toolkit for ASR provides state-of-the-art automatic speech recognition models including Parakeet models for various languages and use cases. urls: - https://github.com/NVIDIA/NeMo tags: - speech-recognition - ASR - NVIDIA capabilities: amd: rocm-nemo default: cpu-nemo intel: intel-nemo metal: metal-nemo nvidia: cuda12-nemo nvidia-cuda-12: cuda12-nemo nvidia-cuda-13: cuda13-nemo uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-nemo mirrors: - localai/localai-backends:latest-gpu-intel-nemo - name: intel-nemo-development alias: nemo license: apache-2.0 icon: https://www.nvidia.com/favicon.ico description: | NVIDIA NEMO Toolkit for ASR provides state-of-the-art automatic speech recognition models including Parakeet models for various languages and use cases. urls: - https://github.com/NVIDIA/NeMo tags: - speech-recognition - ASR - NVIDIA capabilities: amd: rocm-nemo default: cpu-nemo intel: intel-nemo metal: metal-nemo nvidia: cuda12-nemo nvidia-cuda-12: cuda12-nemo nvidia-cuda-13: cuda13-nemo uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-nemo mirrors: - localai/localai-backends:master-gpu-intel-nemo - name: rocm-nemo alias: nemo license: apache-2.0 icon: https://www.nvidia.com/favicon.ico description: | NVIDIA NEMO Toolkit for ASR provides state-of-the-art automatic speech recognition models including Parakeet models for various languages and use cases. urls: - https://github.com/NVIDIA/NeMo tags: - speech-recognition - ASR - NVIDIA capabilities: amd: rocm-nemo default: cpu-nemo intel: intel-nemo metal: metal-nemo nvidia: cuda12-nemo nvidia-cuda-12: cuda12-nemo nvidia-cuda-13: cuda13-nemo uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-nemo mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-nemo - name: rocm-nemo-development alias: nemo license: apache-2.0 icon: https://www.nvidia.com/favicon.ico description: | NVIDIA NEMO Toolkit for ASR provides state-of-the-art automatic speech recognition models including Parakeet models for various languages and use cases. urls: - https://github.com/NVIDIA/NeMo tags: - speech-recognition - ASR - NVIDIA capabilities: amd: rocm-nemo default: cpu-nemo intel: intel-nemo metal: metal-nemo nvidia: cuda12-nemo nvidia-cuda-12: cuda12-nemo nvidia-cuda-13: cuda13-nemo uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-nemo mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-nemo - name: metal-nemo alias: nemo license: apache-2.0 icon: https://www.nvidia.com/favicon.ico description: | NVIDIA NEMO Toolkit for ASR provides state-of-the-art automatic speech recognition models including Parakeet models for various languages and use cases. urls: - https://github.com/NVIDIA/NeMo tags: - speech-recognition - ASR - NVIDIA capabilities: amd: rocm-nemo default: cpu-nemo intel: intel-nemo metal: metal-nemo nvidia: cuda12-nemo nvidia-cuda-12: cuda12-nemo nvidia-cuda-13: cuda13-nemo uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-nemo mirrors: - localai/localai-backends:latest-metal-darwin-arm64-nemo - name: metal-nemo-development alias: nemo license: apache-2.0 icon: https://www.nvidia.com/favicon.ico description: | NVIDIA NEMO Toolkit for ASR provides state-of-the-art automatic speech recognition models including Parakeet models for various languages and use cases. urls: - https://github.com/NVIDIA/NeMo tags: - speech-recognition - ASR - NVIDIA capabilities: amd: rocm-nemo default: cpu-nemo intel: intel-nemo metal: metal-nemo nvidia: cuda12-nemo nvidia-cuda-12: cuda12-nemo nvidia-cuda-13: cuda13-nemo uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-nemo mirrors: - localai/localai-backends:master-metal-darwin-arm64-nemo - name: voxcpm-development alias: voxcpm license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech. urls: - https://github.com/ModelBest/VoxCPM tags: - text-to-speech - TTS capabilities: amd: rocm-voxcpm-development default: cpu-voxcpm-development intel: intel-voxcpm-development metal: metal-voxcpm-development nvidia: cuda12-voxcpm-development nvidia-cuda-12: cuda12-voxcpm-development nvidia-cuda-13: cuda13-voxcpm-development - name: cpu-voxcpm alias: voxcpm license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech. urls: - https://github.com/ModelBest/VoxCPM tags: - text-to-speech - TTS capabilities: amd: rocm-voxcpm default: cpu-voxcpm intel: intel-voxcpm metal: metal-voxcpm nvidia: cuda12-voxcpm nvidia-cuda-12: cuda12-voxcpm nvidia-cuda-13: cuda13-voxcpm uri: quay.io/go-skynet/local-ai-backends:latest-cpu-voxcpm mirrors: - localai/localai-backends:latest-cpu-voxcpm - name: cpu-voxcpm-development alias: voxcpm license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech. urls: - https://github.com/ModelBest/VoxCPM tags: - text-to-speech - TTS capabilities: amd: rocm-voxcpm default: cpu-voxcpm intel: intel-voxcpm metal: metal-voxcpm nvidia: cuda12-voxcpm nvidia-cuda-12: cuda12-voxcpm nvidia-cuda-13: cuda13-voxcpm uri: quay.io/go-skynet/local-ai-backends:master-cpu-voxcpm mirrors: - localai/localai-backends:master-cpu-voxcpm - name: cuda12-voxcpm alias: voxcpm license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech. urls: - https://github.com/ModelBest/VoxCPM tags: - text-to-speech - TTS capabilities: amd: rocm-voxcpm default: cpu-voxcpm intel: intel-voxcpm metal: metal-voxcpm nvidia: cuda12-voxcpm nvidia-cuda-12: cuda12-voxcpm nvidia-cuda-13: cuda13-voxcpm uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-voxcpm mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-voxcpm - name: cuda12-voxcpm-development alias: voxcpm license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech. urls: - https://github.com/ModelBest/VoxCPM tags: - text-to-speech - TTS capabilities: amd: rocm-voxcpm default: cpu-voxcpm intel: intel-voxcpm metal: metal-voxcpm nvidia: cuda12-voxcpm nvidia-cuda-12: cuda12-voxcpm nvidia-cuda-13: cuda13-voxcpm uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-voxcpm mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-voxcpm - name: cuda13-voxcpm alias: voxcpm license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech. urls: - https://github.com/ModelBest/VoxCPM tags: - text-to-speech - TTS capabilities: amd: rocm-voxcpm default: cpu-voxcpm intel: intel-voxcpm metal: metal-voxcpm nvidia: cuda12-voxcpm nvidia-cuda-12: cuda12-voxcpm nvidia-cuda-13: cuda13-voxcpm uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-voxcpm mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-voxcpm - name: cuda13-voxcpm-development alias: voxcpm license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech. urls: - https://github.com/ModelBest/VoxCPM tags: - text-to-speech - TTS capabilities: amd: rocm-voxcpm default: cpu-voxcpm intel: intel-voxcpm metal: metal-voxcpm nvidia: cuda12-voxcpm nvidia-cuda-12: cuda12-voxcpm nvidia-cuda-13: cuda13-voxcpm uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-voxcpm mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-voxcpm - name: intel-voxcpm alias: voxcpm license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech. urls: - https://github.com/ModelBest/VoxCPM tags: - text-to-speech - TTS capabilities: amd: rocm-voxcpm default: cpu-voxcpm intel: intel-voxcpm metal: metal-voxcpm nvidia: cuda12-voxcpm nvidia-cuda-12: cuda12-voxcpm nvidia-cuda-13: cuda13-voxcpm uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-voxcpm mirrors: - localai/localai-backends:latest-gpu-intel-voxcpm - name: intel-voxcpm-development alias: voxcpm license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech. urls: - https://github.com/ModelBest/VoxCPM tags: - text-to-speech - TTS capabilities: amd: rocm-voxcpm default: cpu-voxcpm intel: intel-voxcpm metal: metal-voxcpm nvidia: cuda12-voxcpm nvidia-cuda-12: cuda12-voxcpm nvidia-cuda-13: cuda13-voxcpm uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-voxcpm mirrors: - localai/localai-backends:master-gpu-intel-voxcpm - name: rocm-voxcpm alias: voxcpm license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech. urls: - https://github.com/ModelBest/VoxCPM tags: - text-to-speech - TTS capabilities: amd: rocm-voxcpm default: cpu-voxcpm intel: intel-voxcpm metal: metal-voxcpm nvidia: cuda12-voxcpm nvidia-cuda-12: cuda12-voxcpm nvidia-cuda-13: cuda13-voxcpm uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-voxcpm mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-voxcpm - name: rocm-voxcpm-development alias: voxcpm license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech. urls: - https://github.com/ModelBest/VoxCPM tags: - text-to-speech - TTS capabilities: amd: rocm-voxcpm default: cpu-voxcpm intel: intel-voxcpm metal: metal-voxcpm nvidia: cuda12-voxcpm nvidia-cuda-12: cuda12-voxcpm nvidia-cuda-13: cuda13-voxcpm uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-voxcpm mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-voxcpm - name: metal-voxcpm alias: voxcpm license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech. urls: - https://github.com/ModelBest/VoxCPM tags: - text-to-speech - TTS capabilities: amd: rocm-voxcpm default: cpu-voxcpm intel: intel-voxcpm metal: metal-voxcpm nvidia: cuda12-voxcpm nvidia-cuda-12: cuda12-voxcpm nvidia-cuda-13: cuda13-voxcpm uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-voxcpm mirrors: - localai/localai-backends:latest-metal-darwin-arm64-voxcpm - name: metal-voxcpm-development alias: voxcpm license: mit icon: https://avatars.githubusercontent.com/u/6154722?s=200&v=4 description: | VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech. urls: - https://github.com/ModelBest/VoxCPM tags: - text-to-speech - TTS capabilities: amd: rocm-voxcpm default: cpu-voxcpm intel: intel-voxcpm metal: metal-voxcpm nvidia: cuda12-voxcpm nvidia-cuda-12: cuda12-voxcpm nvidia-cuda-13: cuda13-voxcpm uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-voxcpm mirrors: - localai/localai-backends:master-metal-darwin-arm64-voxcpm - name: pocket-tts-development alias: pocket-tts license: mit icon: https://avatars.githubusercontent.com/u/151010778?s=200&v=4 description: | Pocket TTS is a lightweight text-to-speech model designed to run efficiently on CPUs. urls: - https://github.com/kyutai-labs/pocket-tts tags: - text-to-speech - TTS capabilities: amd: rocm-pocket-tts-development default: cpu-pocket-tts-development intel: intel-pocket-tts-development metal: metal-pocket-tts-development nvidia: cuda12-pocket-tts-development nvidia-cuda-12: cuda12-pocket-tts-development nvidia-cuda-13: cuda13-pocket-tts-development nvidia-l4t: nvidia-l4t-pocket-tts-development nvidia-l4t-cuda-12: nvidia-l4t-pocket-tts-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-pocket-tts-development - name: cpu-pocket-tts alias: pocket-tts license: mit icon: https://avatars.githubusercontent.com/u/151010778?s=200&v=4 description: | Pocket TTS is a lightweight text-to-speech model designed to run efficiently on CPUs. urls: - https://github.com/kyutai-labs/pocket-tts tags: - text-to-speech - TTS capabilities: amd: rocm-pocket-tts default: cpu-pocket-tts intel: intel-pocket-tts metal: metal-pocket-tts nvidia: cuda12-pocket-tts nvidia-cuda-12: cuda12-pocket-tts nvidia-cuda-13: cuda13-pocket-tts nvidia-l4t: nvidia-l4t-pocket-tts nvidia-l4t-cuda-12: nvidia-l4t-pocket-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-pocket-tts uri: quay.io/go-skynet/local-ai-backends:latest-cpu-pocket-tts mirrors: - localai/localai-backends:latest-cpu-pocket-tts - name: cpu-pocket-tts-development alias: pocket-tts license: mit icon: https://avatars.githubusercontent.com/u/151010778?s=200&v=4 description: | Pocket TTS is a lightweight text-to-speech model designed to run efficiently on CPUs. urls: - https://github.com/kyutai-labs/pocket-tts tags: - text-to-speech - TTS capabilities: amd: rocm-pocket-tts default: cpu-pocket-tts intel: intel-pocket-tts metal: metal-pocket-tts nvidia: cuda12-pocket-tts nvidia-cuda-12: cuda12-pocket-tts nvidia-cuda-13: cuda13-pocket-tts nvidia-l4t: nvidia-l4t-pocket-tts nvidia-l4t-cuda-12: nvidia-l4t-pocket-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-pocket-tts uri: quay.io/go-skynet/local-ai-backends:master-cpu-pocket-tts mirrors: - localai/localai-backends:master-cpu-pocket-tts - name: cuda12-pocket-tts alias: pocket-tts license: mit icon: https://avatars.githubusercontent.com/u/151010778?s=200&v=4 description: | Pocket TTS is a lightweight text-to-speech model designed to run efficiently on CPUs. urls: - https://github.com/kyutai-labs/pocket-tts tags: - text-to-speech - TTS capabilities: amd: rocm-pocket-tts default: cpu-pocket-tts intel: intel-pocket-tts metal: metal-pocket-tts nvidia: cuda12-pocket-tts nvidia-cuda-12: cuda12-pocket-tts nvidia-cuda-13: cuda13-pocket-tts nvidia-l4t: nvidia-l4t-pocket-tts nvidia-l4t-cuda-12: nvidia-l4t-pocket-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-pocket-tts uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-pocket-tts mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-pocket-tts - name: cuda12-pocket-tts-development alias: pocket-tts license: mit icon: https://avatars.githubusercontent.com/u/151010778?s=200&v=4 description: | Pocket TTS is a lightweight text-to-speech model designed to run efficiently on CPUs. urls: - https://github.com/kyutai-labs/pocket-tts tags: - text-to-speech - TTS capabilities: amd: rocm-pocket-tts default: cpu-pocket-tts intel: intel-pocket-tts metal: metal-pocket-tts nvidia: cuda12-pocket-tts nvidia-cuda-12: cuda12-pocket-tts nvidia-cuda-13: cuda13-pocket-tts nvidia-l4t: nvidia-l4t-pocket-tts nvidia-l4t-cuda-12: nvidia-l4t-pocket-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-pocket-tts uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-pocket-tts mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-pocket-tts - name: cuda13-pocket-tts alias: pocket-tts license: mit icon: https://avatars.githubusercontent.com/u/151010778?s=200&v=4 description: | Pocket TTS is a lightweight text-to-speech model designed to run efficiently on CPUs. urls: - https://github.com/kyutai-labs/pocket-tts tags: - text-to-speech - TTS capabilities: amd: rocm-pocket-tts default: cpu-pocket-tts intel: intel-pocket-tts metal: metal-pocket-tts nvidia: cuda12-pocket-tts nvidia-cuda-12: cuda12-pocket-tts nvidia-cuda-13: cuda13-pocket-tts nvidia-l4t: nvidia-l4t-pocket-tts nvidia-l4t-cuda-12: nvidia-l4t-pocket-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-pocket-tts uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-pocket-tts mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-pocket-tts - name: cuda13-pocket-tts-development alias: pocket-tts license: mit icon: https://avatars.githubusercontent.com/u/151010778?s=200&v=4 description: | Pocket TTS is a lightweight text-to-speech model designed to run efficiently on CPUs. urls: - https://github.com/kyutai-labs/pocket-tts tags: - text-to-speech - TTS capabilities: amd: rocm-pocket-tts default: cpu-pocket-tts intel: intel-pocket-tts metal: metal-pocket-tts nvidia: cuda12-pocket-tts nvidia-cuda-12: cuda12-pocket-tts nvidia-cuda-13: cuda13-pocket-tts nvidia-l4t: nvidia-l4t-pocket-tts nvidia-l4t-cuda-12: nvidia-l4t-pocket-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-pocket-tts uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-pocket-tts mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-pocket-tts - name: intel-pocket-tts alias: pocket-tts license: mit icon: https://avatars.githubusercontent.com/u/151010778?s=200&v=4 description: | Pocket TTS is a lightweight text-to-speech model designed to run efficiently on CPUs. urls: - https://github.com/kyutai-labs/pocket-tts tags: - text-to-speech - TTS capabilities: amd: rocm-pocket-tts default: cpu-pocket-tts intel: intel-pocket-tts metal: metal-pocket-tts nvidia: cuda12-pocket-tts nvidia-cuda-12: cuda12-pocket-tts nvidia-cuda-13: cuda13-pocket-tts nvidia-l4t: nvidia-l4t-pocket-tts nvidia-l4t-cuda-12: nvidia-l4t-pocket-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-pocket-tts uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-pocket-tts mirrors: - localai/localai-backends:latest-gpu-intel-pocket-tts - name: intel-pocket-tts-development alias: pocket-tts license: mit icon: https://avatars.githubusercontent.com/u/151010778?s=200&v=4 description: | Pocket TTS is a lightweight text-to-speech model designed to run efficiently on CPUs. urls: - https://github.com/kyutai-labs/pocket-tts tags: - text-to-speech - TTS capabilities: amd: rocm-pocket-tts default: cpu-pocket-tts intel: intel-pocket-tts metal: metal-pocket-tts nvidia: cuda12-pocket-tts nvidia-cuda-12: cuda12-pocket-tts nvidia-cuda-13: cuda13-pocket-tts nvidia-l4t: nvidia-l4t-pocket-tts nvidia-l4t-cuda-12: nvidia-l4t-pocket-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-pocket-tts uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-pocket-tts mirrors: - localai/localai-backends:master-gpu-intel-pocket-tts - name: rocm-pocket-tts alias: pocket-tts license: mit icon: https://avatars.githubusercontent.com/u/151010778?s=200&v=4 description: | Pocket TTS is a lightweight text-to-speech model designed to run efficiently on CPUs. urls: - https://github.com/kyutai-labs/pocket-tts tags: - text-to-speech - TTS capabilities: amd: rocm-pocket-tts default: cpu-pocket-tts intel: intel-pocket-tts metal: metal-pocket-tts nvidia: cuda12-pocket-tts nvidia-cuda-12: cuda12-pocket-tts nvidia-cuda-13: cuda13-pocket-tts nvidia-l4t: nvidia-l4t-pocket-tts nvidia-l4t-cuda-12: nvidia-l4t-pocket-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-pocket-tts uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-pocket-tts mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-pocket-tts - name: rocm-pocket-tts-development alias: pocket-tts license: mit icon: https://avatars.githubusercontent.com/u/151010778?s=200&v=4 description: | Pocket TTS is a lightweight text-to-speech model designed to run efficiently on CPUs. urls: - https://github.com/kyutai-labs/pocket-tts tags: - text-to-speech - TTS capabilities: amd: rocm-pocket-tts default: cpu-pocket-tts intel: intel-pocket-tts metal: metal-pocket-tts nvidia: cuda12-pocket-tts nvidia-cuda-12: cuda12-pocket-tts nvidia-cuda-13: cuda13-pocket-tts nvidia-l4t: nvidia-l4t-pocket-tts nvidia-l4t-cuda-12: nvidia-l4t-pocket-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-pocket-tts uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-pocket-tts mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-pocket-tts - name: nvidia-l4t-pocket-tts alias: pocket-tts license: mit icon: https://avatars.githubusercontent.com/u/151010778?s=200&v=4 description: | Pocket TTS is a lightweight text-to-speech model designed to run efficiently on CPUs. urls: - https://github.com/kyutai-labs/pocket-tts tags: - text-to-speech - TTS capabilities: amd: rocm-pocket-tts default: cpu-pocket-tts intel: intel-pocket-tts metal: metal-pocket-tts nvidia: cuda12-pocket-tts nvidia-cuda-12: cuda12-pocket-tts nvidia-cuda-13: cuda13-pocket-tts nvidia-l4t: nvidia-l4t-pocket-tts nvidia-l4t-cuda-12: nvidia-l4t-pocket-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-pocket-tts uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-pocket-tts mirrors: - localai/localai-backends:latest-nvidia-l4t-pocket-tts - name: nvidia-l4t-pocket-tts-development alias: pocket-tts license: mit icon: https://avatars.githubusercontent.com/u/151010778?s=200&v=4 description: | Pocket TTS is a lightweight text-to-speech model designed to run efficiently on CPUs. urls: - https://github.com/kyutai-labs/pocket-tts tags: - text-to-speech - TTS capabilities: amd: rocm-pocket-tts default: cpu-pocket-tts intel: intel-pocket-tts metal: metal-pocket-tts nvidia: cuda12-pocket-tts nvidia-cuda-12: cuda12-pocket-tts nvidia-cuda-13: cuda13-pocket-tts nvidia-l4t: nvidia-l4t-pocket-tts nvidia-l4t-cuda-12: nvidia-l4t-pocket-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-pocket-tts uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-pocket-tts mirrors: - localai/localai-backends:master-nvidia-l4t-pocket-tts - name: cuda13-nvidia-l4t-arm64-pocket-tts alias: pocket-tts license: mit icon: https://avatars.githubusercontent.com/u/151010778?s=200&v=4 description: | Pocket TTS is a lightweight text-to-speech model designed to run efficiently on CPUs. urls: - https://github.com/kyutai-labs/pocket-tts tags: - text-to-speech - TTS capabilities: amd: rocm-pocket-tts default: cpu-pocket-tts intel: intel-pocket-tts metal: metal-pocket-tts nvidia: cuda12-pocket-tts nvidia-cuda-12: cuda12-pocket-tts nvidia-cuda-13: cuda13-pocket-tts nvidia-l4t: nvidia-l4t-pocket-tts nvidia-l4t-cuda-12: nvidia-l4t-pocket-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-pocket-tts uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-pocket-tts mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-pocket-tts - name: cuda13-nvidia-l4t-arm64-pocket-tts-development alias: pocket-tts license: mit icon: https://avatars.githubusercontent.com/u/151010778?s=200&v=4 description: | Pocket TTS is a lightweight text-to-speech model designed to run efficiently on CPUs. urls: - https://github.com/kyutai-labs/pocket-tts tags: - text-to-speech - TTS capabilities: amd: rocm-pocket-tts default: cpu-pocket-tts intel: intel-pocket-tts metal: metal-pocket-tts nvidia: cuda12-pocket-tts nvidia-cuda-12: cuda12-pocket-tts nvidia-cuda-13: cuda13-pocket-tts nvidia-l4t: nvidia-l4t-pocket-tts nvidia-l4t-cuda-12: nvidia-l4t-pocket-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-pocket-tts uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-pocket-tts mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-pocket-tts - name: metal-pocket-tts alias: pocket-tts license: mit icon: https://avatars.githubusercontent.com/u/151010778?s=200&v=4 description: | Pocket TTS is a lightweight text-to-speech model designed to run efficiently on CPUs. urls: - https://github.com/kyutai-labs/pocket-tts tags: - text-to-speech - TTS capabilities: amd: rocm-pocket-tts default: cpu-pocket-tts intel: intel-pocket-tts metal: metal-pocket-tts nvidia: cuda12-pocket-tts nvidia-cuda-12: cuda12-pocket-tts nvidia-cuda-13: cuda13-pocket-tts nvidia-l4t: nvidia-l4t-pocket-tts nvidia-l4t-cuda-12: nvidia-l4t-pocket-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-pocket-tts uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-pocket-tts mirrors: - localai/localai-backends:latest-metal-darwin-arm64-pocket-tts - name: metal-pocket-tts-development alias: pocket-tts license: mit icon: https://avatars.githubusercontent.com/u/151010778?s=200&v=4 description: | Pocket TTS is a lightweight text-to-speech model designed to run efficiently on CPUs. urls: - https://github.com/kyutai-labs/pocket-tts tags: - text-to-speech - TTS capabilities: amd: rocm-pocket-tts default: cpu-pocket-tts intel: intel-pocket-tts metal: metal-pocket-tts nvidia: cuda12-pocket-tts nvidia-cuda-12: cuda12-pocket-tts nvidia-cuda-13: cuda13-pocket-tts nvidia-l4t: nvidia-l4t-pocket-tts nvidia-l4t-cuda-12: nvidia-l4t-pocket-tts nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-pocket-tts uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-pocket-tts mirrors: - localai/localai-backends:master-metal-darwin-arm64-pocket-tts - name: cpu-voxtral alias: voxtral license: mit description: | Voxtral Realtime 4B Pure C speech-to-text inference engine urls: - https://github.com/mudler/voxtral.c tags: - audio-transcription - CPU - Metal capabilities: default: cpu-voxtral metal-darwin-arm64: metal-voxtral uri: quay.io/go-skynet/local-ai-backends:latest-cpu-voxtral mirrors: - localai/localai-backends:latest-cpu-voxtral - name: cpu-voxtral-development alias: voxtral license: mit description: | Voxtral Realtime 4B Pure C speech-to-text inference engine urls: - https://github.com/mudler/voxtral.c tags: - audio-transcription - CPU - Metal capabilities: default: cpu-voxtral metal-darwin-arm64: metal-voxtral uri: quay.io/go-skynet/local-ai-backends:master-cpu-voxtral mirrors: - localai/localai-backends:master-cpu-voxtral - name: metal-voxtral alias: voxtral license: mit description: | Voxtral Realtime 4B Pure C speech-to-text inference engine urls: - https://github.com/mudler/voxtral.c tags: - audio-transcription - CPU - Metal capabilities: default: cpu-voxtral metal-darwin-arm64: metal-voxtral uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-voxtral mirrors: - localai/localai-backends:latest-metal-darwin-arm64-voxtral - name: metal-voxtral-development alias: voxtral license: mit description: | Voxtral Realtime 4B Pure C speech-to-text inference engine urls: - https://github.com/mudler/voxtral.c tags: - audio-transcription - CPU - Metal capabilities: default: cpu-voxtral metal-darwin-arm64: metal-voxtral uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-voxtral mirrors: - localai/localai-backends:master-metal-darwin-arm64-voxtral - name: trl alias: trl license: apache-2.0 description: | HuggingFace TRL fine-tuning backend. Supports SFT, DPO, GRPO, RLOO, Reward, KTO, ORPO training methods. Works on CPU and GPU. urls: - https://github.com/huggingface/trl tags: - fine-tuning - LLM - CPU - GPU - CUDA capabilities: default: cpu-trl metal: metal-trl nvidia: cuda12-trl nvidia-cuda-12: cuda12-trl nvidia-cuda-13: cuda13-trl - name: cpu-trl alias: trl license: apache-2.0 description: | HuggingFace TRL fine-tuning backend. Supports SFT, DPO, GRPO, RLOO, Reward, KTO, ORPO training methods. Works on CPU and GPU. urls: - https://github.com/huggingface/trl tags: - fine-tuning - LLM - CPU - GPU - CUDA capabilities: default: cpu-trl metal: metal-trl nvidia: cuda12-trl nvidia-cuda-12: cuda12-trl nvidia-cuda-13: cuda13-trl uri: quay.io/go-skynet/local-ai-backends:latest-cpu-trl mirrors: - localai/localai-backends:latest-cpu-trl - name: cpu-trl-development alias: trl license: apache-2.0 description: | HuggingFace TRL fine-tuning backend. Supports SFT, DPO, GRPO, RLOO, Reward, KTO, ORPO training methods. Works on CPU and GPU. urls: - https://github.com/huggingface/trl tags: - fine-tuning - LLM - CPU - GPU - CUDA capabilities: default: cpu-trl metal: metal-trl nvidia: cuda12-trl nvidia-cuda-12: cuda12-trl nvidia-cuda-13: cuda13-trl uri: quay.io/go-skynet/local-ai-backends:master-cpu-trl mirrors: - localai/localai-backends:master-cpu-trl - name: cuda12-trl alias: trl license: apache-2.0 description: | HuggingFace TRL fine-tuning backend. Supports SFT, DPO, GRPO, RLOO, Reward, KTO, ORPO training methods. Works on CPU and GPU. urls: - https://github.com/huggingface/trl tags: - fine-tuning - LLM - CPU - GPU - CUDA capabilities: default: cpu-trl metal: metal-trl nvidia: cuda12-trl nvidia-cuda-12: cuda12-trl nvidia-cuda-13: cuda13-trl uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-trl mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-trl - name: cuda12-trl-development alias: trl license: apache-2.0 description: | HuggingFace TRL fine-tuning backend. Supports SFT, DPO, GRPO, RLOO, Reward, KTO, ORPO training methods. Works on CPU and GPU. urls: - https://github.com/huggingface/trl tags: - fine-tuning - LLM - CPU - GPU - CUDA capabilities: default: cpu-trl metal: metal-trl nvidia: cuda12-trl nvidia-cuda-12: cuda12-trl nvidia-cuda-13: cuda13-trl uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-trl mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-trl - name: cuda13-trl alias: trl license: apache-2.0 description: | HuggingFace TRL fine-tuning backend. Supports SFT, DPO, GRPO, RLOO, Reward, KTO, ORPO training methods. Works on CPU and GPU. urls: - https://github.com/huggingface/trl tags: - fine-tuning - LLM - CPU - GPU - CUDA capabilities: default: cpu-trl metal: metal-trl nvidia: cuda12-trl nvidia-cuda-12: cuda12-trl nvidia-cuda-13: cuda13-trl uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-trl mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-trl - name: cuda13-trl-development alias: trl license: apache-2.0 description: | HuggingFace TRL fine-tuning backend. Supports SFT, DPO, GRPO, RLOO, Reward, KTO, ORPO training methods. Works on CPU and GPU. urls: - https://github.com/huggingface/trl tags: - fine-tuning - LLM - CPU - GPU - CUDA capabilities: default: cpu-trl metal: metal-trl nvidia: cuda12-trl nvidia-cuda-12: cuda12-trl nvidia-cuda-13: cuda13-trl uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-trl mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-trl - name: metal-trl alias: trl license: apache-2.0 description: | HuggingFace TRL fine-tuning backend. Supports SFT, DPO, GRPO, RLOO, Reward, KTO, ORPO training methods. Works on CPU and GPU. urls: - https://github.com/huggingface/trl tags: - fine-tuning - LLM - CPU - GPU - CUDA capabilities: default: cpu-trl metal: metal-trl nvidia: cuda12-trl nvidia-cuda-12: cuda12-trl nvidia-cuda-13: cuda13-trl uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-trl mirrors: - localai/localai-backends:latest-metal-darwin-arm64-trl - name: metal-trl-development alias: trl license: apache-2.0 description: | HuggingFace TRL fine-tuning backend. Supports SFT, DPO, GRPO, RLOO, Reward, KTO, ORPO training methods. Works on CPU and GPU. urls: - https://github.com/huggingface/trl tags: - fine-tuning - LLM - CPU - GPU - CUDA capabilities: default: cpu-trl metal: metal-trl nvidia: cuda12-trl nvidia-cuda-12: cuda12-trl nvidia-cuda-13: cuda13-trl uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-trl mirrors: - localai/localai-backends:master-metal-darwin-arm64-trl - name: llama-cpp-quantization alias: llama-cpp-quantization license: mit icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png description: | Model quantization backend using llama.cpp. Downloads HuggingFace models, converts them to GGUF format, and quantizes them to various formats (q4_k_m, q5_k_m, q8_0, f16, etc.). urls: - https://github.com/ggml-org/llama.cpp tags: - quantization - GGUF - CPU capabilities: default: cpu-llama-cpp-quantization metal: metal-darwin-arm64-llama-cpp-quantization - name: cpu-llama-cpp-quantization alias: llama-cpp-quantization license: mit icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png description: | Model quantization backend using llama.cpp. Downloads HuggingFace models, converts them to GGUF format, and quantizes them to various formats (q4_k_m, q5_k_m, q8_0, f16, etc.). urls: - https://github.com/ggml-org/llama.cpp tags: - quantization - GGUF - CPU capabilities: default: cpu-llama-cpp-quantization metal: metal-darwin-arm64-llama-cpp-quantization uri: quay.io/go-skynet/local-ai-backends:latest-cpu-llama-cpp-quantization mirrors: - localai/localai-backends:latest-cpu-llama-cpp-quantization - name: metal-darwin-arm64-llama-cpp-quantization alias: llama-cpp-quantization license: mit icon: https://user-images.githubusercontent.com/1991296/230134379-7181e485-c521-4d23-a0d6-f7b3b61ba524.png description: | Model quantization backend using llama.cpp. Downloads HuggingFace models, converts them to GGUF format, and quantizes them to various formats (q4_k_m, q5_k_m, q8_0, f16, etc.). urls: - https://github.com/ggml-org/llama.cpp tags: - quantization - GGUF - CPU capabilities: default: cpu-llama-cpp-quantization metal: metal-darwin-arm64-llama-cpp-quantization uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-llama-cpp-quantization mirrors: - localai/localai-backends:latest-metal-darwin-arm64-llama-cpp-quantization - name: insightface-development alias: insightface license: mixed description: | Face recognition backend powered by `insightface` (ONNX Runtime). Provides face verification (/v1/face/verify), face analysis (/v1/face/analyze), face embedding (/v1/embeddings), face detection (/v1/detection), and 1:N identification (/v1/face/{register,identify,forget}). Ships two engines in a single image: one that drives the insightface model packs (buffalo_l/s/m/sc, antelopev2 — non-commercial research use only) and one that drives OpenCV Zoo's YuNet + SFace pair (Apache 2.0 — commercial-safe). Select via `options: ["engine:..."]` in your model YAML, or install one of the ready-made model-gallery entries under the `insightface-*` prefix. The backend image contains only code and Python deps; all model weights are managed by LocalAI's gallery download mechanism. urls: - https://github.com/deepinsight/insightface - https://github.com/opencv/opencv_zoo tags: - face-recognition - face-verification - face-embedding - gpu - cpu capabilities: default: cpu-insightface-development nvidia: cuda12-insightface-development nvidia-cuda-12: cuda12-insightface-development - name: cpu-insightface alias: insightface license: mixed description: | Face recognition backend powered by `insightface` (ONNX Runtime). Provides face verification (/v1/face/verify), face analysis (/v1/face/analyze), face embedding (/v1/embeddings), face detection (/v1/detection), and 1:N identification (/v1/face/{register,identify,forget}). Ships two engines in a single image: one that drives the insightface model packs (buffalo_l/s/m/sc, antelopev2 — non-commercial research use only) and one that drives OpenCV Zoo's YuNet + SFace pair (Apache 2.0 — commercial-safe). Select via `options: ["engine:..."]` in your model YAML, or install one of the ready-made model-gallery entries under the `insightface-*` prefix. The backend image contains only code and Python deps; all model weights are managed by LocalAI's gallery download mechanism. urls: - https://github.com/deepinsight/insightface - https://github.com/opencv/opencv_zoo tags: - face-recognition - face-verification - face-embedding - gpu - cpu capabilities: default: cpu-insightface nvidia: cuda12-insightface nvidia-cuda-12: cuda12-insightface uri: quay.io/go-skynet/local-ai-backends:latest-cpu-insightface mirrors: - localai/localai-backends:latest-cpu-insightface - name: cuda12-insightface alias: insightface license: mixed description: | Face recognition backend powered by `insightface` (ONNX Runtime). Provides face verification (/v1/face/verify), face analysis (/v1/face/analyze), face embedding (/v1/embeddings), face detection (/v1/detection), and 1:N identification (/v1/face/{register,identify,forget}). Ships two engines in a single image: one that drives the insightface model packs (buffalo_l/s/m/sc, antelopev2 — non-commercial research use only) and one that drives OpenCV Zoo's YuNet + SFace pair (Apache 2.0 — commercial-safe). Select via `options: ["engine:..."]` in your model YAML, or install one of the ready-made model-gallery entries under the `insightface-*` prefix. The backend image contains only code and Python deps; all model weights are managed by LocalAI's gallery download mechanism. urls: - https://github.com/deepinsight/insightface - https://github.com/opencv/opencv_zoo tags: - face-recognition - face-verification - face-embedding - gpu - cpu capabilities: default: cpu-insightface nvidia: cuda12-insightface nvidia-cuda-12: cuda12-insightface uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-insightface mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-insightface - name: cpu-insightface-development alias: insightface license: mixed description: | Face recognition backend powered by `insightface` (ONNX Runtime). Provides face verification (/v1/face/verify), face analysis (/v1/face/analyze), face embedding (/v1/embeddings), face detection (/v1/detection), and 1:N identification (/v1/face/{register,identify,forget}). Ships two engines in a single image: one that drives the insightface model packs (buffalo_l/s/m/sc, antelopev2 — non-commercial research use only) and one that drives OpenCV Zoo's YuNet + SFace pair (Apache 2.0 — commercial-safe). Select via `options: ["engine:..."]` in your model YAML, or install one of the ready-made model-gallery entries under the `insightface-*` prefix. The backend image contains only code and Python deps; all model weights are managed by LocalAI's gallery download mechanism. urls: - https://github.com/deepinsight/insightface - https://github.com/opencv/opencv_zoo tags: - face-recognition - face-verification - face-embedding - gpu - cpu capabilities: default: cpu-insightface nvidia: cuda12-insightface nvidia-cuda-12: cuda12-insightface uri: quay.io/go-skynet/local-ai-backends:master-cpu-insightface mirrors: - localai/localai-backends:master-cpu-insightface - name: cuda12-insightface-development alias: insightface license: mixed description: | Face recognition backend powered by `insightface` (ONNX Runtime). Provides face verification (/v1/face/verify), face analysis (/v1/face/analyze), face embedding (/v1/embeddings), face detection (/v1/detection), and 1:N identification (/v1/face/{register,identify,forget}). Ships two engines in a single image: one that drives the insightface model packs (buffalo_l/s/m/sc, antelopev2 — non-commercial research use only) and one that drives OpenCV Zoo's YuNet + SFace pair (Apache 2.0 — commercial-safe). Select via `options: ["engine:..."]` in your model YAML, or install one of the ready-made model-gallery entries under the `insightface-*` prefix. The backend image contains only code and Python deps; all model weights are managed by LocalAI's gallery download mechanism. urls: - https://github.com/deepinsight/insightface - https://github.com/opencv/opencv_zoo tags: - face-recognition - face-verification - face-embedding - gpu - cpu capabilities: default: cpu-insightface nvidia: cuda12-insightface nvidia-cuda-12: cuda12-insightface uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-insightface mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-insightface - name: speaker-recognition alias: speaker-recognition license: apache-2.0 description: | Speaker (voice) recognition backend — the audio analog to insightface. Wraps SpeechBrain ECAPA-TDNN (default engine, 192-d embeddings, ~1.9% EER on VoxCeleb) plus an OnnxDirectEngine for pre-exported WeSpeaker / 3D-Speaker ONNX models. Exposes speaker verification (/v1/voice/verify), speaker embedding (/v1/voice/embed), speaker analysis (/v1/voice/analyze), and 1:N speaker identification (/v1/voice/{register,identify,forget}). Registrations use LocalAI's built-in vector store — same in-memory backing the face-recognition registry uses, separate instance. urls: - https://speechbrain.github.io/ - https://github.com/wenet-e2e/wespeaker - https://github.com/modelscope/3D-Speaker tags: - voice-recognition - speaker-verification - speaker-embedding - gpu - cpu capabilities: default: cpu-speaker-recognition metal: metal-speaker-recognition nvidia: cuda12-speaker-recognition nvidia-cuda-12: cuda12-speaker-recognition - name: speaker-recognition-development alias: speaker-recognition license: apache-2.0 description: | Speaker (voice) recognition backend — the audio analog to insightface. Wraps SpeechBrain ECAPA-TDNN (default engine, 192-d embeddings, ~1.9% EER on VoxCeleb) plus an OnnxDirectEngine for pre-exported WeSpeaker / 3D-Speaker ONNX models. Exposes speaker verification (/v1/voice/verify), speaker embedding (/v1/voice/embed), speaker analysis (/v1/voice/analyze), and 1:N speaker identification (/v1/voice/{register,identify,forget}). Registrations use LocalAI's built-in vector store — same in-memory backing the face-recognition registry uses, separate instance. urls: - https://speechbrain.github.io/ - https://github.com/wenet-e2e/wespeaker - https://github.com/modelscope/3D-Speaker tags: - voice-recognition - speaker-verification - speaker-embedding - gpu - cpu capabilities: default: cpu-speaker-recognition-development metal: metal-speaker-recognition-development nvidia: cuda12-speaker-recognition-development nvidia-cuda-12: cuda12-speaker-recognition-development - name: cpu-speaker-recognition alias: speaker-recognition license: apache-2.0 description: | Speaker (voice) recognition backend — the audio analog to insightface. Wraps SpeechBrain ECAPA-TDNN (default engine, 192-d embeddings, ~1.9% EER on VoxCeleb) plus an OnnxDirectEngine for pre-exported WeSpeaker / 3D-Speaker ONNX models. Exposes speaker verification (/v1/voice/verify), speaker embedding (/v1/voice/embed), speaker analysis (/v1/voice/analyze), and 1:N speaker identification (/v1/voice/{register,identify,forget}). Registrations use LocalAI's built-in vector store — same in-memory backing the face-recognition registry uses, separate instance. urls: - https://speechbrain.github.io/ - https://github.com/wenet-e2e/wespeaker - https://github.com/modelscope/3D-Speaker tags: - voice-recognition - speaker-verification - speaker-embedding - gpu - cpu capabilities: default: cpu-speaker-recognition metal: metal-speaker-recognition nvidia: cuda12-speaker-recognition nvidia-cuda-12: cuda12-speaker-recognition uri: quay.io/go-skynet/local-ai-backends:latest-cpu-speaker-recognition mirrors: - localai/localai-backends:latest-cpu-speaker-recognition - name: cuda12-speaker-recognition alias: speaker-recognition license: apache-2.0 description: | Speaker (voice) recognition backend — the audio analog to insightface. Wraps SpeechBrain ECAPA-TDNN (default engine, 192-d embeddings, ~1.9% EER on VoxCeleb) plus an OnnxDirectEngine for pre-exported WeSpeaker / 3D-Speaker ONNX models. Exposes speaker verification (/v1/voice/verify), speaker embedding (/v1/voice/embed), speaker analysis (/v1/voice/analyze), and 1:N speaker identification (/v1/voice/{register,identify,forget}). Registrations use LocalAI's built-in vector store — same in-memory backing the face-recognition registry uses, separate instance. urls: - https://speechbrain.github.io/ - https://github.com/wenet-e2e/wespeaker - https://github.com/modelscope/3D-Speaker tags: - voice-recognition - speaker-verification - speaker-embedding - gpu - cpu capabilities: default: cpu-speaker-recognition metal: metal-speaker-recognition nvidia: cuda12-speaker-recognition nvidia-cuda-12: cuda12-speaker-recognition uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-speaker-recognition mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-speaker-recognition - name: cpu-speaker-recognition-development alias: speaker-recognition license: apache-2.0 description: | Speaker (voice) recognition backend — the audio analog to insightface. Wraps SpeechBrain ECAPA-TDNN (default engine, 192-d embeddings, ~1.9% EER on VoxCeleb) plus an OnnxDirectEngine for pre-exported WeSpeaker / 3D-Speaker ONNX models. Exposes speaker verification (/v1/voice/verify), speaker embedding (/v1/voice/embed), speaker analysis (/v1/voice/analyze), and 1:N speaker identification (/v1/voice/{register,identify,forget}). Registrations use LocalAI's built-in vector store — same in-memory backing the face-recognition registry uses, separate instance. urls: - https://speechbrain.github.io/ - https://github.com/wenet-e2e/wespeaker - https://github.com/modelscope/3D-Speaker tags: - voice-recognition - speaker-verification - speaker-embedding - gpu - cpu capabilities: default: cpu-speaker-recognition metal: metal-speaker-recognition nvidia: cuda12-speaker-recognition nvidia-cuda-12: cuda12-speaker-recognition uri: quay.io/go-skynet/local-ai-backends:master-cpu-speaker-recognition mirrors: - localai/localai-backends:master-cpu-speaker-recognition - name: cuda12-speaker-recognition-development alias: speaker-recognition license: apache-2.0 description: | Speaker (voice) recognition backend — the audio analog to insightface. Wraps SpeechBrain ECAPA-TDNN (default engine, 192-d embeddings, ~1.9% EER on VoxCeleb) plus an OnnxDirectEngine for pre-exported WeSpeaker / 3D-Speaker ONNX models. Exposes speaker verification (/v1/voice/verify), speaker embedding (/v1/voice/embed), speaker analysis (/v1/voice/analyze), and 1:N speaker identification (/v1/voice/{register,identify,forget}). Registrations use LocalAI's built-in vector store — same in-memory backing the face-recognition registry uses, separate instance. urls: - https://speechbrain.github.io/ - https://github.com/wenet-e2e/wespeaker - https://github.com/modelscope/3D-Speaker tags: - voice-recognition - speaker-verification - speaker-embedding - gpu - cpu capabilities: default: cpu-speaker-recognition metal: metal-speaker-recognition nvidia: cuda12-speaker-recognition nvidia-cuda-12: cuda12-speaker-recognition uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-speaker-recognition mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-speaker-recognition - name: metal-speaker-recognition alias: speaker-recognition license: apache-2.0 description: | Speaker (voice) recognition backend — the audio analog to insightface. Wraps SpeechBrain ECAPA-TDNN (default engine, 192-d embeddings, ~1.9% EER on VoxCeleb) plus an OnnxDirectEngine for pre-exported WeSpeaker / 3D-Speaker ONNX models. Exposes speaker verification (/v1/voice/verify), speaker embedding (/v1/voice/embed), speaker analysis (/v1/voice/analyze), and 1:N speaker identification (/v1/voice/{register,identify,forget}). Registrations use LocalAI's built-in vector store — same in-memory backing the face-recognition registry uses, separate instance. urls: - https://speechbrain.github.io/ - https://github.com/wenet-e2e/wespeaker - https://github.com/modelscope/3D-Speaker tags: - voice-recognition - speaker-verification - speaker-embedding - gpu - cpu capabilities: default: cpu-speaker-recognition metal: metal-speaker-recognition nvidia: cuda12-speaker-recognition nvidia-cuda-12: cuda12-speaker-recognition uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-speaker-recognition mirrors: - localai/localai-backends:latest-metal-darwin-arm64-speaker-recognition - name: metal-speaker-recognition-development alias: speaker-recognition license: apache-2.0 description: | Speaker (voice) recognition backend — the audio analog to insightface. Wraps SpeechBrain ECAPA-TDNN (default engine, 192-d embeddings, ~1.9% EER on VoxCeleb) plus an OnnxDirectEngine for pre-exported WeSpeaker / 3D-Speaker ONNX models. Exposes speaker verification (/v1/voice/verify), speaker embedding (/v1/voice/embed), speaker analysis (/v1/voice/analyze), and 1:N speaker identification (/v1/voice/{register,identify,forget}). Registrations use LocalAI's built-in vector store — same in-memory backing the face-recognition registry uses, separate instance. urls: - https://speechbrain.github.io/ - https://github.com/wenet-e2e/wespeaker - https://github.com/modelscope/3D-Speaker tags: - voice-recognition - speaker-verification - speaker-embedding - gpu - cpu capabilities: default: cpu-speaker-recognition metal: metal-speaker-recognition nvidia: cuda12-speaker-recognition nvidia-cuda-12: cuda12-speaker-recognition uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-speaker-recognition mirrors: - localai/localai-backends:master-metal-darwin-arm64-speaker-recognition - name: sherpa-onnx-development alias: sherpa-onnx description: | Sherpa-ONNX backend for text-to-speech (VITS, Matcha, Kokoro), speech-to-text (Whisper, Paraformer, SenseVoice, Omnilingual ASR CTC), and voice activity detection via ONNX Runtime. Supports multi-speaker voices, 1600+ language ASR, and GPU acceleration. urls: - https://k2-fsa.github.io/sherpa/onnx/ tags: - text-to-speech - TTS - speech-to-text - ASR capabilities: default: cpu-sherpa-onnx-development metal: metal-sherpa-onnx-development nvidia: cuda12-sherpa-onnx-development nvidia-cuda-12: cuda12-sherpa-onnx-development - name: cpu-sherpa-onnx alias: sherpa-onnx description: | Sherpa-ONNX backend for text-to-speech (VITS, Matcha, Kokoro), speech-to-text (Whisper, Paraformer, SenseVoice, Omnilingual ASR CTC), and voice activity detection via ONNX Runtime. Supports multi-speaker voices, 1600+ language ASR, and GPU acceleration. urls: - https://k2-fsa.github.io/sherpa/onnx/ tags: - text-to-speech - TTS - speech-to-text - ASR capabilities: default: cpu-sherpa-onnx metal: metal-sherpa-onnx nvidia: cuda12-sherpa-onnx nvidia-cuda-12: cuda12-sherpa-onnx uri: quay.io/go-skynet/local-ai-backends:latest-cpu-sherpa-onnx mirrors: - localai/localai-backends:latest-cpu-sherpa-onnx - name: cpu-sherpa-onnx-development alias: sherpa-onnx description: | Sherpa-ONNX backend for text-to-speech (VITS, Matcha, Kokoro), speech-to-text (Whisper, Paraformer, SenseVoice, Omnilingual ASR CTC), and voice activity detection via ONNX Runtime. Supports multi-speaker voices, 1600+ language ASR, and GPU acceleration. urls: - https://k2-fsa.github.io/sherpa/onnx/ tags: - text-to-speech - TTS - speech-to-text - ASR capabilities: default: cpu-sherpa-onnx metal: metal-sherpa-onnx nvidia: cuda12-sherpa-onnx nvidia-cuda-12: cuda12-sherpa-onnx uri: quay.io/go-skynet/local-ai-backends:master-cpu-sherpa-onnx mirrors: - localai/localai-backends:master-cpu-sherpa-onnx - name: cuda12-sherpa-onnx alias: sherpa-onnx description: | Sherpa-ONNX backend for text-to-speech (VITS, Matcha, Kokoro), speech-to-text (Whisper, Paraformer, SenseVoice, Omnilingual ASR CTC), and voice activity detection via ONNX Runtime. Supports multi-speaker voices, 1600+ language ASR, and GPU acceleration. urls: - https://k2-fsa.github.io/sherpa/onnx/ tags: - text-to-speech - TTS - speech-to-text - ASR capabilities: default: cpu-sherpa-onnx metal: metal-sherpa-onnx nvidia: cuda12-sherpa-onnx nvidia-cuda-12: cuda12-sherpa-onnx uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-sherpa-onnx mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-sherpa-onnx - name: cuda12-sherpa-onnx-development alias: sherpa-onnx description: | Sherpa-ONNX backend for text-to-speech (VITS, Matcha, Kokoro), speech-to-text (Whisper, Paraformer, SenseVoice, Omnilingual ASR CTC), and voice activity detection via ONNX Runtime. Supports multi-speaker voices, 1600+ language ASR, and GPU acceleration. urls: - https://k2-fsa.github.io/sherpa/onnx/ tags: - text-to-speech - TTS - speech-to-text - ASR capabilities: default: cpu-sherpa-onnx metal: metal-sherpa-onnx nvidia: cuda12-sherpa-onnx nvidia-cuda-12: cuda12-sherpa-onnx uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-sherpa-onnx mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-sherpa-onnx - name: metal-sherpa-onnx alias: sherpa-onnx description: | Sherpa-ONNX backend for text-to-speech (VITS, Matcha, Kokoro), speech-to-text (Whisper, Paraformer, SenseVoice, Omnilingual ASR CTC), and voice activity detection via ONNX Runtime. Supports multi-speaker voices, 1600+ language ASR, and GPU acceleration. urls: - https://k2-fsa.github.io/sherpa/onnx/ tags: - text-to-speech - TTS - speech-to-text - ASR capabilities: default: cpu-sherpa-onnx metal: metal-sherpa-onnx nvidia: cuda12-sherpa-onnx nvidia-cuda-12: cuda12-sherpa-onnx uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-sherpa-onnx mirrors: - localai/localai-backends:latest-metal-darwin-arm64-sherpa-onnx - name: metal-sherpa-onnx-development alias: sherpa-onnx description: | Sherpa-ONNX backend for text-to-speech (VITS, Matcha, Kokoro), speech-to-text (Whisper, Paraformer, SenseVoice, Omnilingual ASR CTC), and voice activity detection via ONNX Runtime. Supports multi-speaker voices, 1600+ language ASR, and GPU acceleration. urls: - https://k2-fsa.github.io/sherpa/onnx/ tags: - text-to-speech - TTS - speech-to-text - ASR capabilities: default: cpu-sherpa-onnx metal: metal-sherpa-onnx nvidia: cuda12-sherpa-onnx nvidia-cuda-12: cuda12-sherpa-onnx uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-sherpa-onnx mirrors: - localai/localai-backends:master-metal-darwin-arm64-sherpa-onnx - name: supertonic-development alias: supertonic description: | Supertonic backend: lightning-fast, on-device multilingual text-to-speech via ONNX Runtime. Runs Supertone's flow-matching TTS model (Supertone/supertonic-3), 44.1kHz output, 31 languages, multiple preset voice styles. No espeak-ng dependency. urls: - https://github.com/supertone-inc/supertonic tags: - text-to-speech - TTS capabilities: default: cpu-supertonic-development metal: metal-supertonic-development - name: cpu-supertonic alias: supertonic description: | Supertonic backend: lightning-fast, on-device multilingual text-to-speech via ONNX Runtime. Runs Supertone's flow-matching TTS model (Supertone/supertonic-3), 44.1kHz output, 31 languages, multiple preset voice styles. No espeak-ng dependency. urls: - https://github.com/supertone-inc/supertonic tags: - text-to-speech - TTS capabilities: default: cpu-supertonic metal: metal-supertonic uri: quay.io/go-skynet/local-ai-backends:latest-cpu-supertonic mirrors: - localai/localai-backends:latest-cpu-supertonic - name: cpu-supertonic-development alias: supertonic description: | Supertonic backend: lightning-fast, on-device multilingual text-to-speech via ONNX Runtime. Runs Supertone's flow-matching TTS model (Supertone/supertonic-3), 44.1kHz output, 31 languages, multiple preset voice styles. No espeak-ng dependency. urls: - https://github.com/supertone-inc/supertonic tags: - text-to-speech - TTS capabilities: default: cpu-supertonic metal: metal-supertonic uri: quay.io/go-skynet/local-ai-backends:master-cpu-supertonic mirrors: - localai/localai-backends:master-cpu-supertonic - name: metal-supertonic alias: supertonic description: | Supertonic backend: lightning-fast, on-device multilingual text-to-speech via ONNX Runtime. Runs Supertone's flow-matching TTS model (Supertone/supertonic-3), 44.1kHz output, 31 languages, multiple preset voice styles. No espeak-ng dependency. urls: - https://github.com/supertone-inc/supertonic tags: - text-to-speech - TTS capabilities: default: cpu-supertonic metal: metal-supertonic uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-supertonic mirrors: - localai/localai-backends:latest-metal-darwin-arm64-supertonic - name: metal-supertonic-development alias: supertonic description: | Supertonic backend: lightning-fast, on-device multilingual text-to-speech via ONNX Runtime. Runs Supertone's flow-matching TTS model (Supertone/supertonic-3), 44.1kHz output, 31 languages, multiple preset voice styles. No espeak-ng dependency. urls: - https://github.com/supertone-inc/supertonic tags: - text-to-speech - TTS capabilities: default: cpu-supertonic metal: metal-supertonic uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-supertonic mirrors: - localai/localai-backends:master-metal-darwin-arm64-supertonic - name: cpu-vllm-cpp alias: vllm-cpp license: apache-2.0 description: | ALPHA development builds. Try it, but llama-cpp stays the recommendation for production use. vllm.cpp is an Apache-2.0 C++20 inference engine maintained by the LocalAI team, developed in its own repository and usable without LocalAI. It began as a port of vLLM and keeps vLLM as its reference implementation, checking output against it and benchmarking against it, while growing a featureset of its own. It implements vLLM's V1 architecture (paged KV cache, continuous batching, prefix caching, scheduler, sampler) on a portable tensor runtime with no Python, PyTorch or ggml at inference time. It loads GGUF as well as Hugging Face safetensors, supports structured output (JSON schema / regex / choice / GBNF grammar) enforced in-engine, ships speculative decoding and KV offload, and runs on CPU, NVIDIA CUDA (Blackwell-family), Apple Metal and Vulkan. The project is expected to be renamed as it diverges further from vLLM; the new name is still to be decided. urls: - https://github.com/mudler/vllm.cpp tags: - text-to-text - LLM - CPU - GPU - CUDA - metal capabilities: default: cpu-vllm-cpp metal: metal-vllm-cpp nvidia: cuda13-vllm-cpp nvidia-cuda-13: cuda13-vllm-cpp nvidia-l4t: nvidia-l4t-arm64-vllm-cpp nvidia-l4t-cuda-13: nvidia-l4t-arm64-vllm-cpp vulkan: vulkan-vllm-cpp uri: quay.io/go-skynet/local-ai-backends:latest-cpu-vllm-cpp mirrors: - localai/localai-backends:latest-cpu-vllm-cpp - name: cpu-vllm-cpp-development alias: vllm-cpp license: apache-2.0 description: | ALPHA development builds. Try it, but llama-cpp stays the recommendation for production use. vllm.cpp is an Apache-2.0 C++20 inference engine maintained by the LocalAI team, developed in its own repository and usable without LocalAI. It began as a port of vLLM and keeps vLLM as its reference implementation, checking output against it and benchmarking against it, while growing a featureset of its own. It implements vLLM's V1 architecture (paged KV cache, continuous batching, prefix caching, scheduler, sampler) on a portable tensor runtime with no Python, PyTorch or ggml at inference time. It loads GGUF as well as Hugging Face safetensors, supports structured output (JSON schema / regex / choice / GBNF grammar) enforced in-engine, ships speculative decoding and KV offload, and runs on CPU, NVIDIA CUDA (Blackwell-family), Apple Metal and Vulkan. The project is expected to be renamed as it diverges further from vLLM; the new name is still to be decided. urls: - https://github.com/mudler/vllm.cpp tags: - text-to-text - LLM - CPU - GPU - CUDA - metal capabilities: default: cpu-vllm-cpp metal: metal-vllm-cpp nvidia: cuda13-vllm-cpp nvidia-cuda-13: cuda13-vllm-cpp nvidia-l4t: nvidia-l4t-arm64-vllm-cpp nvidia-l4t-cuda-13: nvidia-l4t-arm64-vllm-cpp vulkan: vulkan-vllm-cpp uri: quay.io/go-skynet/local-ai-backends:master-cpu-vllm-cpp mirrors: - localai/localai-backends:master-cpu-vllm-cpp - name: cuda13-vllm-cpp alias: vllm-cpp license: apache-2.0 description: | ALPHA development builds. Try it, but llama-cpp stays the recommendation for production use. vllm.cpp is an Apache-2.0 C++20 inference engine maintained by the LocalAI team, developed in its own repository and usable without LocalAI. It began as a port of vLLM and keeps vLLM as its reference implementation, checking output against it and benchmarking against it, while growing a featureset of its own. It implements vLLM's V1 architecture (paged KV cache, continuous batching, prefix caching, scheduler, sampler) on a portable tensor runtime with no Python, PyTorch or ggml at inference time. It loads GGUF as well as Hugging Face safetensors, supports structured output (JSON schema / regex / choice / GBNF grammar) enforced in-engine, ships speculative decoding and KV offload, and runs on CPU, NVIDIA CUDA (Blackwell-family), Apple Metal and Vulkan. The project is expected to be renamed as it diverges further from vLLM; the new name is still to be decided. urls: - https://github.com/mudler/vllm.cpp tags: - text-to-text - LLM - CPU - GPU - CUDA - metal capabilities: default: cpu-vllm-cpp metal: metal-vllm-cpp nvidia: cuda13-vllm-cpp nvidia-cuda-13: cuda13-vllm-cpp nvidia-l4t: nvidia-l4t-arm64-vllm-cpp nvidia-l4t-cuda-13: nvidia-l4t-arm64-vllm-cpp vulkan: vulkan-vllm-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-vllm-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-vllm-cpp - name: cuda13-vllm-cpp-development alias: vllm-cpp license: apache-2.0 description: | ALPHA development builds. Try it, but llama-cpp stays the recommendation for production use. vllm.cpp is an Apache-2.0 C++20 inference engine maintained by the LocalAI team, developed in its own repository and usable without LocalAI. It began as a port of vLLM and keeps vLLM as its reference implementation, checking output against it and benchmarking against it, while growing a featureset of its own. It implements vLLM's V1 architecture (paged KV cache, continuous batching, prefix caching, scheduler, sampler) on a portable tensor runtime with no Python, PyTorch or ggml at inference time. It loads GGUF as well as Hugging Face safetensors, supports structured output (JSON schema / regex / choice / GBNF grammar) enforced in-engine, ships speculative decoding and KV offload, and runs on CPU, NVIDIA CUDA (Blackwell-family), Apple Metal and Vulkan. The project is expected to be renamed as it diverges further from vLLM; the new name is still to be decided. urls: - https://github.com/mudler/vllm.cpp tags: - text-to-text - LLM - CPU - GPU - CUDA - metal capabilities: default: cpu-vllm-cpp metal: metal-vllm-cpp nvidia: cuda13-vllm-cpp nvidia-cuda-13: cuda13-vllm-cpp nvidia-l4t: nvidia-l4t-arm64-vllm-cpp nvidia-l4t-cuda-13: nvidia-l4t-arm64-vllm-cpp vulkan: vulkan-vllm-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-vllm-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-vllm-cpp - name: nvidia-l4t-arm64-vllm-cpp alias: vllm-cpp license: apache-2.0 description: | ALPHA development builds. Try it, but llama-cpp stays the recommendation for production use. vllm.cpp is an Apache-2.0 C++20 inference engine maintained by the LocalAI team, developed in its own repository and usable without LocalAI. It began as a port of vLLM and keeps vLLM as its reference implementation, checking output against it and benchmarking against it, while growing a featureset of its own. It implements vLLM's V1 architecture (paged KV cache, continuous batching, prefix caching, scheduler, sampler) on a portable tensor runtime with no Python, PyTorch or ggml at inference time. It loads GGUF as well as Hugging Face safetensors, supports structured output (JSON schema / regex / choice / GBNF grammar) enforced in-engine, ships speculative decoding and KV offload, and runs on CPU, NVIDIA CUDA (Blackwell-family), Apple Metal and Vulkan. The project is expected to be renamed as it diverges further from vLLM; the new name is still to be decided. urls: - https://github.com/mudler/vllm.cpp tags: - text-to-text - LLM - CPU - GPU - CUDA - metal capabilities: default: cpu-vllm-cpp metal: metal-vllm-cpp nvidia: cuda13-vllm-cpp nvidia-cuda-13: cuda13-vllm-cpp nvidia-l4t: nvidia-l4t-arm64-vllm-cpp nvidia-l4t-cuda-13: nvidia-l4t-arm64-vllm-cpp vulkan: vulkan-vllm-cpp uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-vllm-cpp mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-vllm-cpp - name: nvidia-l4t-arm64-vllm-cpp-development alias: vllm-cpp license: apache-2.0 description: | ALPHA development builds. Try it, but llama-cpp stays the recommendation for production use. vllm.cpp is an Apache-2.0 C++20 inference engine maintained by the LocalAI team, developed in its own repository and usable without LocalAI. It began as a port of vLLM and keeps vLLM as its reference implementation, checking output against it and benchmarking against it, while growing a featureset of its own. It implements vLLM's V1 architecture (paged KV cache, continuous batching, prefix caching, scheduler, sampler) on a portable tensor runtime with no Python, PyTorch or ggml at inference time. It loads GGUF as well as Hugging Face safetensors, supports structured output (JSON schema / regex / choice / GBNF grammar) enforced in-engine, ships speculative decoding and KV offload, and runs on CPU, NVIDIA CUDA (Blackwell-family), Apple Metal and Vulkan. The project is expected to be renamed as it diverges further from vLLM; the new name is still to be decided. urls: - https://github.com/mudler/vllm.cpp tags: - text-to-text - LLM - CPU - GPU - CUDA - metal capabilities: default: cpu-vllm-cpp metal: metal-vllm-cpp nvidia: cuda13-vllm-cpp nvidia-cuda-13: cuda13-vllm-cpp nvidia-l4t: nvidia-l4t-arm64-vllm-cpp nvidia-l4t-cuda-13: nvidia-l4t-arm64-vllm-cpp vulkan: vulkan-vllm-cpp uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-vllm-cpp mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-vllm-cpp - name: vulkan-vllm-cpp alias: vllm-cpp license: apache-2.0 description: | ALPHA development builds. Try it, but llama-cpp stays the recommendation for production use. vllm.cpp is an Apache-2.0 C++20 inference engine maintained by the LocalAI team, developed in its own repository and usable without LocalAI. It began as a port of vLLM and keeps vLLM as its reference implementation, checking output against it and benchmarking against it, while growing a featureset of its own. It implements vLLM's V1 architecture (paged KV cache, continuous batching, prefix caching, scheduler, sampler) on a portable tensor runtime with no Python, PyTorch or ggml at inference time. It loads GGUF as well as Hugging Face safetensors, supports structured output (JSON schema / regex / choice / GBNF grammar) enforced in-engine, ships speculative decoding and KV offload, and runs on CPU, NVIDIA CUDA (Blackwell-family), Apple Metal and Vulkan. The project is expected to be renamed as it diverges further from vLLM; the new name is still to be decided. urls: - https://github.com/mudler/vllm.cpp tags: - text-to-text - LLM - CPU - GPU - CUDA - metal capabilities: default: cpu-vllm-cpp metal: metal-vllm-cpp nvidia: cuda13-vllm-cpp nvidia-cuda-13: cuda13-vllm-cpp nvidia-l4t: nvidia-l4t-arm64-vllm-cpp nvidia-l4t-cuda-13: nvidia-l4t-arm64-vllm-cpp vulkan: vulkan-vllm-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-vllm-cpp mirrors: - localai/localai-backends:latest-gpu-vulkan-vllm-cpp - name: vulkan-vllm-cpp-development alias: vllm-cpp license: apache-2.0 description: | ALPHA development builds. Try it, but llama-cpp stays the recommendation for production use. vllm.cpp is an Apache-2.0 C++20 inference engine maintained by the LocalAI team, developed in its own repository and usable without LocalAI. It began as a port of vLLM and keeps vLLM as its reference implementation, checking output against it and benchmarking against it, while growing a featureset of its own. It implements vLLM's V1 architecture (paged KV cache, continuous batching, prefix caching, scheduler, sampler) on a portable tensor runtime with no Python, PyTorch or ggml at inference time. It loads GGUF as well as Hugging Face safetensors, supports structured output (JSON schema / regex / choice / GBNF grammar) enforced in-engine, ships speculative decoding and KV offload, and runs on CPU, NVIDIA CUDA (Blackwell-family), Apple Metal and Vulkan. The project is expected to be renamed as it diverges further from vLLM; the new name is still to be decided. urls: - https://github.com/mudler/vllm.cpp tags: - text-to-text - LLM - CPU - GPU - CUDA - metal capabilities: default: cpu-vllm-cpp metal: metal-vllm-cpp nvidia: cuda13-vllm-cpp nvidia-cuda-13: cuda13-vllm-cpp nvidia-l4t: nvidia-l4t-arm64-vllm-cpp nvidia-l4t-cuda-13: nvidia-l4t-arm64-vllm-cpp vulkan: vulkan-vllm-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-vllm-cpp mirrors: - localai/localai-backends:master-gpu-vulkan-vllm-cpp - name: metal-vllm-cpp alias: vllm-cpp license: apache-2.0 description: | ALPHA development builds. Try it, but llama-cpp stays the recommendation for production use. vllm.cpp is an Apache-2.0 C++20 inference engine maintained by the LocalAI team, developed in its own repository and usable without LocalAI. It began as a port of vLLM and keeps vLLM as its reference implementation, checking output against it and benchmarking against it, while growing a featureset of its own. It implements vLLM's V1 architecture (paged KV cache, continuous batching, prefix caching, scheduler, sampler) on a portable tensor runtime with no Python, PyTorch or ggml at inference time. It loads GGUF as well as Hugging Face safetensors, supports structured output (JSON schema / regex / choice / GBNF grammar) enforced in-engine, ships speculative decoding and KV offload, and runs on CPU, NVIDIA CUDA (Blackwell-family), Apple Metal and Vulkan. The project is expected to be renamed as it diverges further from vLLM; the new name is still to be decided. urls: - https://github.com/mudler/vllm.cpp tags: - text-to-text - LLM - CPU - GPU - CUDA - metal capabilities: default: cpu-vllm-cpp metal: metal-vllm-cpp nvidia: cuda13-vllm-cpp nvidia-cuda-13: cuda13-vllm-cpp nvidia-l4t: nvidia-l4t-arm64-vllm-cpp nvidia-l4t-cuda-13: nvidia-l4t-arm64-vllm-cpp vulkan: vulkan-vllm-cpp uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-vllm-cpp mirrors: - localai/localai-backends:latest-metal-darwin-arm64-vllm-cpp - name: metal-vllm-cpp-development alias: vllm-cpp license: apache-2.0 description: | ALPHA development builds. Try it, but llama-cpp stays the recommendation for production use. vllm.cpp is an Apache-2.0 C++20 inference engine maintained by the LocalAI team, developed in its own repository and usable without LocalAI. It began as a port of vLLM and keeps vLLM as its reference implementation, checking output against it and benchmarking against it, while growing a featureset of its own. It implements vLLM's V1 architecture (paged KV cache, continuous batching, prefix caching, scheduler, sampler) on a portable tensor runtime with no Python, PyTorch or ggml at inference time. It loads GGUF as well as Hugging Face safetensors, supports structured output (JSON schema / regex / choice / GBNF grammar) enforced in-engine, ships speculative decoding and KV offload, and runs on CPU, NVIDIA CUDA (Blackwell-family), Apple Metal and Vulkan. The project is expected to be renamed as it diverges further from vLLM; the new name is still to be decided. urls: - https://github.com/mudler/vllm.cpp tags: - text-to-text - LLM - CPU - GPU - CUDA - metal capabilities: default: cpu-vllm-cpp metal: metal-vllm-cpp nvidia: cuda13-vllm-cpp nvidia-cuda-13: cuda13-vllm-cpp nvidia-l4t: nvidia-l4t-arm64-vllm-cpp nvidia-l4t-cuda-13: nvidia-l4t-arm64-vllm-cpp vulkan: vulkan-vllm-cpp uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-vllm-cpp mirrors: - localai/localai-backends:master-metal-darwin-arm64-vllm-cpp - name: cpu-audio-cpp alias: audio-cpp license: apache-2.0 description: | 0xShug0/audio.cpp - a ggml audio inference framework covering text to speech, voice cloning, transcription, forced alignment, voice activity detection, speaker diarization, source separation, voice conversion and music generation, across 30+ model families. Consumes audio.cpp-native GGUF packages from huggingface.co/audio-cpp/audio.cpp-gguf. urls: - https://github.com/0xShug0/audio.cpp - https://huggingface.co/audio-cpp/audio.cpp-gguf tags: - TTS - text-to-speech - audio-transcription - CPU - CUDA - HIP - Metal capabilities: amd: rocm-audio-cpp default: cpu-audio-cpp metal: metal-audio-cpp metal-darwin-arm64: metal-audio-cpp nvidia: cuda12-audio-cpp nvidia-cuda-12: cuda12-audio-cpp nvidia-cuda-13: cuda13-audio-cpp uri: quay.io/go-skynet/local-ai-backends:latest-cpu-audio-cpp mirrors: - localai/localai-backends:latest-cpu-audio-cpp - name: cpu-audio-cpp-development alias: audio-cpp license: apache-2.0 description: | 0xShug0/audio.cpp - a ggml audio inference framework covering text to speech, voice cloning, transcription, forced alignment, voice activity detection, speaker diarization, source separation, voice conversion and music generation, across 30+ model families. Consumes audio.cpp-native GGUF packages from huggingface.co/audio-cpp/audio.cpp-gguf. urls: - https://github.com/0xShug0/audio.cpp - https://huggingface.co/audio-cpp/audio.cpp-gguf tags: - TTS - text-to-speech - audio-transcription - CPU - CUDA - HIP - Metal capabilities: amd: rocm-audio-cpp default: cpu-audio-cpp metal: metal-audio-cpp metal-darwin-arm64: metal-audio-cpp nvidia: cuda12-audio-cpp nvidia-cuda-12: cuda12-audio-cpp nvidia-cuda-13: cuda13-audio-cpp uri: quay.io/go-skynet/local-ai-backends:master-cpu-audio-cpp mirrors: - localai/localai-backends:master-cpu-audio-cpp - name: cuda12-audio-cpp alias: audio-cpp license: apache-2.0 description: | 0xShug0/audio.cpp - a ggml audio inference framework covering text to speech, voice cloning, transcription, forced alignment, voice activity detection, speaker diarization, source separation, voice conversion and music generation, across 30+ model families. Consumes audio.cpp-native GGUF packages from huggingface.co/audio-cpp/audio.cpp-gguf. urls: - https://github.com/0xShug0/audio.cpp - https://huggingface.co/audio-cpp/audio.cpp-gguf tags: - TTS - text-to-speech - audio-transcription - CPU - CUDA - HIP - Metal capabilities: amd: rocm-audio-cpp default: cpu-audio-cpp metal: metal-audio-cpp metal-darwin-arm64: metal-audio-cpp nvidia: cuda12-audio-cpp nvidia-cuda-12: cuda12-audio-cpp nvidia-cuda-13: cuda13-audio-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-audio-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-audio-cpp - name: cuda12-audio-cpp-development alias: audio-cpp license: apache-2.0 description: | 0xShug0/audio.cpp - a ggml audio inference framework covering text to speech, voice cloning, transcription, forced alignment, voice activity detection, speaker diarization, source separation, voice conversion and music generation, across 30+ model families. Consumes audio.cpp-native GGUF packages from huggingface.co/audio-cpp/audio.cpp-gguf. urls: - https://github.com/0xShug0/audio.cpp - https://huggingface.co/audio-cpp/audio.cpp-gguf tags: - TTS - text-to-speech - audio-transcription - CPU - CUDA - HIP - Metal capabilities: amd: rocm-audio-cpp default: cpu-audio-cpp metal: metal-audio-cpp metal-darwin-arm64: metal-audio-cpp nvidia: cuda12-audio-cpp nvidia-cuda-12: cuda12-audio-cpp nvidia-cuda-13: cuda13-audio-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-audio-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-audio-cpp - name: cuda13-audio-cpp alias: audio-cpp license: apache-2.0 description: | 0xShug0/audio.cpp - a ggml audio inference framework covering text to speech, voice cloning, transcription, forced alignment, voice activity detection, speaker diarization, source separation, voice conversion and music generation, across 30+ model families. Consumes audio.cpp-native GGUF packages from huggingface.co/audio-cpp/audio.cpp-gguf. urls: - https://github.com/0xShug0/audio.cpp - https://huggingface.co/audio-cpp/audio.cpp-gguf tags: - TTS - text-to-speech - audio-transcription - CPU - CUDA - HIP - Metal capabilities: amd: rocm-audio-cpp default: cpu-audio-cpp metal: metal-audio-cpp metal-darwin-arm64: metal-audio-cpp nvidia: cuda12-audio-cpp nvidia-cuda-12: cuda12-audio-cpp nvidia-cuda-13: cuda13-audio-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-audio-cpp mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-audio-cpp - name: cuda13-audio-cpp-development alias: audio-cpp license: apache-2.0 description: | 0xShug0/audio.cpp - a ggml audio inference framework covering text to speech, voice cloning, transcription, forced alignment, voice activity detection, speaker diarization, source separation, voice conversion and music generation, across 30+ model families. Consumes audio.cpp-native GGUF packages from huggingface.co/audio-cpp/audio.cpp-gguf. urls: - https://github.com/0xShug0/audio.cpp - https://huggingface.co/audio-cpp/audio.cpp-gguf tags: - TTS - text-to-speech - audio-transcription - CPU - CUDA - HIP - Metal capabilities: amd: rocm-audio-cpp default: cpu-audio-cpp metal: metal-audio-cpp metal-darwin-arm64: metal-audio-cpp nvidia: cuda12-audio-cpp nvidia-cuda-12: cuda12-audio-cpp nvidia-cuda-13: cuda13-audio-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-audio-cpp mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-audio-cpp - name: rocm-audio-cpp alias: audio-cpp license: apache-2.0 description: | 0xShug0/audio.cpp - a ggml audio inference framework covering text to speech, voice cloning, transcription, forced alignment, voice activity detection, speaker diarization, source separation, voice conversion and music generation, across 30+ model families. Consumes audio.cpp-native GGUF packages from huggingface.co/audio-cpp/audio.cpp-gguf. urls: - https://github.com/0xShug0/audio.cpp - https://huggingface.co/audio-cpp/audio.cpp-gguf tags: - TTS - text-to-speech - audio-transcription - CPU - CUDA - HIP - Metal capabilities: amd: rocm-audio-cpp default: cpu-audio-cpp metal: metal-audio-cpp metal-darwin-arm64: metal-audio-cpp nvidia: cuda12-audio-cpp nvidia-cuda-12: cuda12-audio-cpp nvidia-cuda-13: cuda13-audio-cpp uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-audio-cpp mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-audio-cpp - name: rocm-audio-cpp-development alias: audio-cpp license: apache-2.0 description: | 0xShug0/audio.cpp - a ggml audio inference framework covering text to speech, voice cloning, transcription, forced alignment, voice activity detection, speaker diarization, source separation, voice conversion and music generation, across 30+ model families. Consumes audio.cpp-native GGUF packages from huggingface.co/audio-cpp/audio.cpp-gguf. urls: - https://github.com/0xShug0/audio.cpp - https://huggingface.co/audio-cpp/audio.cpp-gguf tags: - TTS - text-to-speech - audio-transcription - CPU - CUDA - HIP - Metal capabilities: amd: rocm-audio-cpp default: cpu-audio-cpp metal: metal-audio-cpp metal-darwin-arm64: metal-audio-cpp nvidia: cuda12-audio-cpp nvidia-cuda-12: cuda12-audio-cpp nvidia-cuda-13: cuda13-audio-cpp uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-audio-cpp mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-audio-cpp - name: metal-audio-cpp alias: audio-cpp license: apache-2.0 description: | 0xShug0/audio.cpp - a ggml audio inference framework covering text to speech, voice cloning, transcription, forced alignment, voice activity detection, speaker diarization, source separation, voice conversion and music generation, across 30+ model families. Consumes audio.cpp-native GGUF packages from huggingface.co/audio-cpp/audio.cpp-gguf. urls: - https://github.com/0xShug0/audio.cpp - https://huggingface.co/audio-cpp/audio.cpp-gguf tags: - TTS - text-to-speech - audio-transcription - CPU - CUDA - HIP - Metal capabilities: amd: rocm-audio-cpp default: cpu-audio-cpp metal: metal-audio-cpp metal-darwin-arm64: metal-audio-cpp nvidia: cuda12-audio-cpp nvidia-cuda-12: cuda12-audio-cpp nvidia-cuda-13: cuda13-audio-cpp uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-audio-cpp mirrors: - localai/localai-backends:latest-metal-darwin-arm64-audio-cpp - name: metal-audio-cpp-development alias: audio-cpp license: apache-2.0 description: | 0xShug0/audio.cpp - a ggml audio inference framework covering text to speech, voice cloning, transcription, forced alignment, voice activity detection, speaker diarization, source separation, voice conversion and music generation, across 30+ model families. Consumes audio.cpp-native GGUF packages from huggingface.co/audio-cpp/audio.cpp-gguf. urls: - https://github.com/0xShug0/audio.cpp - https://huggingface.co/audio-cpp/audio.cpp-gguf tags: - TTS - text-to-speech - audio-transcription - CPU - CUDA - HIP - Metal capabilities: amd: rocm-audio-cpp default: cpu-audio-cpp metal: metal-audio-cpp metal-darwin-arm64: metal-audio-cpp nvidia: cuda12-audio-cpp nvidia-cuda-12: cuda12-audio-cpp nvidia-cuda-13: cuda13-audio-cpp uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-audio-cpp mirrors: - localai/localai-backends:master-metal-darwin-arm64-audio-cpp - name: funasr-development alias: funasr license: mit icon: https://avatars.githubusercontent.com/u/109454077 description: | FunASR is an industrial-grade speech recognition toolkit supporting 50+ languages. Includes SenseVoice (170x realtime, emotion detection), Paraformer (highest Chinese accuracy), and built-in VAD, punctuation restoration, and speaker diarization. urls: - https://github.com/modelscope/FunASR tags: - speech-recognition - ASR - multilingual capabilities: amd: rocm-funasr-development default: cpu-funasr-development intel: intel-funasr-development metal: metal-funasr-development nvidia: cuda12-funasr-development nvidia-cuda-12: cuda12-funasr-development nvidia-cuda-13: cuda13-funasr-development nvidia-l4t: nvidia-l4t-funasr-development nvidia-l4t-cuda-12: nvidia-l4t-funasr-development nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-funasr-development - name: cpu-funasr alias: funasr license: mit icon: https://avatars.githubusercontent.com/u/109454077 description: | FunASR is an industrial-grade speech recognition toolkit supporting 50+ languages. Includes SenseVoice (170x realtime, emotion detection), Paraformer (highest Chinese accuracy), and built-in VAD, punctuation restoration, and speaker diarization. urls: - https://github.com/modelscope/FunASR tags: - speech-recognition - ASR - multilingual capabilities: amd: rocm-funasr default: cpu-funasr intel: intel-funasr metal: metal-funasr nvidia: cuda12-funasr nvidia-cuda-12: cuda12-funasr nvidia-cuda-13: cuda13-funasr nvidia-l4t: nvidia-l4t-funasr nvidia-l4t-cuda-12: nvidia-l4t-funasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-funasr uri: quay.io/go-skynet/local-ai-backends:latest-cpu-funasr mirrors: - localai/localai-backends:latest-cpu-funasr - name: cpu-funasr-development alias: funasr license: mit icon: https://avatars.githubusercontent.com/u/109454077 description: | FunASR is an industrial-grade speech recognition toolkit supporting 50+ languages. Includes SenseVoice (170x realtime, emotion detection), Paraformer (highest Chinese accuracy), and built-in VAD, punctuation restoration, and speaker diarization. urls: - https://github.com/modelscope/FunASR tags: - speech-recognition - ASR - multilingual capabilities: amd: rocm-funasr default: cpu-funasr intel: intel-funasr metal: metal-funasr nvidia: cuda12-funasr nvidia-cuda-12: cuda12-funasr nvidia-cuda-13: cuda13-funasr nvidia-l4t: nvidia-l4t-funasr nvidia-l4t-cuda-12: nvidia-l4t-funasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-funasr uri: quay.io/go-skynet/local-ai-backends:master-cpu-funasr mirrors: - localai/localai-backends:master-cpu-funasr - name: cuda12-funasr alias: funasr license: mit icon: https://avatars.githubusercontent.com/u/109454077 description: | FunASR is an industrial-grade speech recognition toolkit supporting 50+ languages. Includes SenseVoice (170x realtime, emotion detection), Paraformer (highest Chinese accuracy), and built-in VAD, punctuation restoration, and speaker diarization. urls: - https://github.com/modelscope/FunASR tags: - speech-recognition - ASR - multilingual capabilities: amd: rocm-funasr default: cpu-funasr intel: intel-funasr metal: metal-funasr nvidia: cuda12-funasr nvidia-cuda-12: cuda12-funasr nvidia-cuda-13: cuda13-funasr nvidia-l4t: nvidia-l4t-funasr nvidia-l4t-cuda-12: nvidia-l4t-funasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-funasr uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-funasr mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-12-funasr - name: cuda12-funasr-development alias: funasr license: mit icon: https://avatars.githubusercontent.com/u/109454077 description: | FunASR is an industrial-grade speech recognition toolkit supporting 50+ languages. Includes SenseVoice (170x realtime, emotion detection), Paraformer (highest Chinese accuracy), and built-in VAD, punctuation restoration, and speaker diarization. urls: - https://github.com/modelscope/FunASR tags: - speech-recognition - ASR - multilingual capabilities: amd: rocm-funasr default: cpu-funasr intel: intel-funasr metal: metal-funasr nvidia: cuda12-funasr nvidia-cuda-12: cuda12-funasr nvidia-cuda-13: cuda13-funasr nvidia-l4t: nvidia-l4t-funasr nvidia-l4t-cuda-12: nvidia-l4t-funasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-funasr uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-funasr mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-12-funasr - name: cuda13-funasr alias: funasr license: mit icon: https://avatars.githubusercontent.com/u/109454077 description: | FunASR is an industrial-grade speech recognition toolkit supporting 50+ languages. Includes SenseVoice (170x realtime, emotion detection), Paraformer (highest Chinese accuracy), and built-in VAD, punctuation restoration, and speaker diarization. urls: - https://github.com/modelscope/FunASR tags: - speech-recognition - ASR - multilingual capabilities: amd: rocm-funasr default: cpu-funasr intel: intel-funasr metal: metal-funasr nvidia: cuda12-funasr nvidia-cuda-12: cuda12-funasr nvidia-cuda-13: cuda13-funasr nvidia-l4t: nvidia-l4t-funasr nvidia-l4t-cuda-12: nvidia-l4t-funasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-funasr uri: quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-funasr mirrors: - localai/localai-backends:latest-gpu-nvidia-cuda-13-funasr - name: cuda13-funasr-development alias: funasr license: mit icon: https://avatars.githubusercontent.com/u/109454077 description: | FunASR is an industrial-grade speech recognition toolkit supporting 50+ languages. Includes SenseVoice (170x realtime, emotion detection), Paraformer (highest Chinese accuracy), and built-in VAD, punctuation restoration, and speaker diarization. urls: - https://github.com/modelscope/FunASR tags: - speech-recognition - ASR - multilingual capabilities: amd: rocm-funasr default: cpu-funasr intel: intel-funasr metal: metal-funasr nvidia: cuda12-funasr nvidia-cuda-12: cuda12-funasr nvidia-cuda-13: cuda13-funasr nvidia-l4t: nvidia-l4t-funasr nvidia-l4t-cuda-12: nvidia-l4t-funasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-funasr uri: quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-funasr mirrors: - localai/localai-backends:master-gpu-nvidia-cuda-13-funasr - name: intel-funasr alias: funasr license: mit icon: https://avatars.githubusercontent.com/u/109454077 description: | FunASR is an industrial-grade speech recognition toolkit supporting 50+ languages. Includes SenseVoice (170x realtime, emotion detection), Paraformer (highest Chinese accuracy), and built-in VAD, punctuation restoration, and speaker diarization. urls: - https://github.com/modelscope/FunASR tags: - speech-recognition - ASR - multilingual capabilities: amd: rocm-funasr default: cpu-funasr intel: intel-funasr metal: metal-funasr nvidia: cuda12-funasr nvidia-cuda-12: cuda12-funasr nvidia-cuda-13: cuda13-funasr nvidia-l4t: nvidia-l4t-funasr nvidia-l4t-cuda-12: nvidia-l4t-funasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-funasr uri: quay.io/go-skynet/local-ai-backends:latest-gpu-intel-funasr mirrors: - localai/localai-backends:latest-gpu-intel-funasr - name: intel-funasr-development alias: funasr license: mit icon: https://avatars.githubusercontent.com/u/109454077 description: | FunASR is an industrial-grade speech recognition toolkit supporting 50+ languages. Includes SenseVoice (170x realtime, emotion detection), Paraformer (highest Chinese accuracy), and built-in VAD, punctuation restoration, and speaker diarization. urls: - https://github.com/modelscope/FunASR tags: - speech-recognition - ASR - multilingual capabilities: amd: rocm-funasr default: cpu-funasr intel: intel-funasr metal: metal-funasr nvidia: cuda12-funasr nvidia-cuda-12: cuda12-funasr nvidia-cuda-13: cuda13-funasr nvidia-l4t: nvidia-l4t-funasr nvidia-l4t-cuda-12: nvidia-l4t-funasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-funasr uri: quay.io/go-skynet/local-ai-backends:master-gpu-intel-funasr mirrors: - localai/localai-backends:master-gpu-intel-funasr - name: rocm-funasr alias: funasr license: mit icon: https://avatars.githubusercontent.com/u/109454077 description: | FunASR is an industrial-grade speech recognition toolkit supporting 50+ languages. Includes SenseVoice (170x realtime, emotion detection), Paraformer (highest Chinese accuracy), and built-in VAD, punctuation restoration, and speaker diarization. urls: - https://github.com/modelscope/FunASR tags: - speech-recognition - ASR - multilingual capabilities: amd: rocm-funasr default: cpu-funasr intel: intel-funasr metal: metal-funasr nvidia: cuda12-funasr nvidia-cuda-12: cuda12-funasr nvidia-cuda-13: cuda13-funasr nvidia-l4t: nvidia-l4t-funasr nvidia-l4t-cuda-12: nvidia-l4t-funasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-funasr uri: quay.io/go-skynet/local-ai-backends:latest-gpu-rocm-hipblas-funasr mirrors: - localai/localai-backends:latest-gpu-rocm-hipblas-funasr - name: rocm-funasr-development alias: funasr license: mit icon: https://avatars.githubusercontent.com/u/109454077 description: | FunASR is an industrial-grade speech recognition toolkit supporting 50+ languages. Includes SenseVoice (170x realtime, emotion detection), Paraformer (highest Chinese accuracy), and built-in VAD, punctuation restoration, and speaker diarization. urls: - https://github.com/modelscope/FunASR tags: - speech-recognition - ASR - multilingual capabilities: amd: rocm-funasr default: cpu-funasr intel: intel-funasr metal: metal-funasr nvidia: cuda12-funasr nvidia-cuda-12: cuda12-funasr nvidia-cuda-13: cuda13-funasr nvidia-l4t: nvidia-l4t-funasr nvidia-l4t-cuda-12: nvidia-l4t-funasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-funasr uri: quay.io/go-skynet/local-ai-backends:master-gpu-rocm-hipblas-funasr mirrors: - localai/localai-backends:master-gpu-rocm-hipblas-funasr - name: nvidia-l4t-funasr alias: funasr license: mit icon: https://avatars.githubusercontent.com/u/109454077 description: | FunASR is an industrial-grade speech recognition toolkit supporting 50+ languages. Includes SenseVoice (170x realtime, emotion detection), Paraformer (highest Chinese accuracy), and built-in VAD, punctuation restoration, and speaker diarization. urls: - https://github.com/modelscope/FunASR tags: - speech-recognition - ASR - multilingual capabilities: amd: rocm-funasr default: cpu-funasr intel: intel-funasr metal: metal-funasr nvidia: cuda12-funasr nvidia-cuda-12: cuda12-funasr nvidia-cuda-13: cuda13-funasr nvidia-l4t: nvidia-l4t-funasr nvidia-l4t-cuda-12: nvidia-l4t-funasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-funasr uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-funasr mirrors: - localai/localai-backends:latest-nvidia-l4t-funasr - name: nvidia-l4t-funasr-development alias: funasr license: mit icon: https://avatars.githubusercontent.com/u/109454077 description: | FunASR is an industrial-grade speech recognition toolkit supporting 50+ languages. Includes SenseVoice (170x realtime, emotion detection), Paraformer (highest Chinese accuracy), and built-in VAD, punctuation restoration, and speaker diarization. urls: - https://github.com/modelscope/FunASR tags: - speech-recognition - ASR - multilingual capabilities: amd: rocm-funasr default: cpu-funasr intel: intel-funasr metal: metal-funasr nvidia: cuda12-funasr nvidia-cuda-12: cuda12-funasr nvidia-cuda-13: cuda13-funasr nvidia-l4t: nvidia-l4t-funasr nvidia-l4t-cuda-12: nvidia-l4t-funasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-funasr uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-funasr mirrors: - localai/localai-backends:master-nvidia-l4t-funasr - name: cuda13-nvidia-l4t-arm64-funasr alias: funasr license: mit icon: https://avatars.githubusercontent.com/u/109454077 description: | FunASR is an industrial-grade speech recognition toolkit supporting 50+ languages. Includes SenseVoice (170x realtime, emotion detection), Paraformer (highest Chinese accuracy), and built-in VAD, punctuation restoration, and speaker diarization. urls: - https://github.com/modelscope/FunASR tags: - speech-recognition - ASR - multilingual capabilities: amd: rocm-funasr default: cpu-funasr intel: intel-funasr metal: metal-funasr nvidia: cuda12-funasr nvidia-cuda-12: cuda12-funasr nvidia-cuda-13: cuda13-funasr nvidia-l4t: nvidia-l4t-funasr nvidia-l4t-cuda-12: nvidia-l4t-funasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-funasr uri: quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-funasr mirrors: - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-funasr - name: cuda13-nvidia-l4t-arm64-funasr-development alias: funasr license: mit icon: https://avatars.githubusercontent.com/u/109454077 description: | FunASR is an industrial-grade speech recognition toolkit supporting 50+ languages. Includes SenseVoice (170x realtime, emotion detection), Paraformer (highest Chinese accuracy), and built-in VAD, punctuation restoration, and speaker diarization. urls: - https://github.com/modelscope/FunASR tags: - speech-recognition - ASR - multilingual capabilities: amd: rocm-funasr default: cpu-funasr intel: intel-funasr metal: metal-funasr nvidia: cuda12-funasr nvidia-cuda-12: cuda12-funasr nvidia-cuda-13: cuda13-funasr nvidia-l4t: nvidia-l4t-funasr nvidia-l4t-cuda-12: nvidia-l4t-funasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-funasr uri: quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-funasr mirrors: - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-funasr - name: metal-funasr alias: funasr license: mit icon: https://avatars.githubusercontent.com/u/109454077 description: | FunASR is an industrial-grade speech recognition toolkit supporting 50+ languages. Includes SenseVoice (170x realtime, emotion detection), Paraformer (highest Chinese accuracy), and built-in VAD, punctuation restoration, and speaker diarization. urls: - https://github.com/modelscope/FunASR tags: - speech-recognition - ASR - multilingual capabilities: amd: rocm-funasr default: cpu-funasr intel: intel-funasr metal: metal-funasr nvidia: cuda12-funasr nvidia-cuda-12: cuda12-funasr nvidia-cuda-13: cuda13-funasr nvidia-l4t: nvidia-l4t-funasr nvidia-l4t-cuda-12: nvidia-l4t-funasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-funasr uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-funasr mirrors: - localai/localai-backends:latest-metal-darwin-arm64-funasr - name: metal-funasr-development alias: funasr license: mit icon: https://avatars.githubusercontent.com/u/109454077 description: | FunASR is an industrial-grade speech recognition toolkit supporting 50+ languages. Includes SenseVoice (170x realtime, emotion detection), Paraformer (highest Chinese accuracy), and built-in VAD, punctuation restoration, and speaker diarization. urls: - https://github.com/modelscope/FunASR tags: - speech-recognition - ASR - multilingual capabilities: amd: rocm-funasr default: cpu-funasr intel: intel-funasr metal: metal-funasr nvidia: cuda12-funasr nvidia-cuda-12: cuda12-funasr nvidia-cuda-13: cuda13-funasr nvidia-l4t: nvidia-l4t-funasr nvidia-l4t-cuda-12: nvidia-l4t-funasr nvidia-l4t-cuda-13: cuda13-nvidia-l4t-arm64-funasr uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-funasr mirrors: - localai/localai-backends:master-metal-darwin-arm64-funasr - name: timestral-cpp alias: timestral-cpp license: mit description: | timestral.cpp is a C++/ggml port of Mistral's Timestral time-series forecasting models. It takes numeric series, with optional covariates, and returns quantile forecasts through POST /v1/forecast. CPU only. The code is MIT; the model weights have their own licence. urls: - https://github.com/mudler/timestral.cpp tags: - forecasting - time-series - CPU capabilities: default: cpu-timestral-cpp metal: metal-timestral-cpp - name: timestral-cpp-development alias: timestral-cpp license: mit description: | timestral.cpp is a C++/ggml port of Mistral's Timestral time-series forecasting models. It takes numeric series, with optional covariates, and returns quantile forecasts through POST /v1/forecast. CPU only. The code is MIT; the model weights have their own licence. urls: - https://github.com/mudler/timestral.cpp tags: - forecasting - time-series - CPU capabilities: default: cpu-timestral-cpp-development metal: metal-timestral-cpp-development - name: cpu-timestral-cpp alias: timestral-cpp license: mit description: | timestral.cpp is a C++/ggml port of Mistral's Timestral time-series forecasting models. It takes numeric series, with optional covariates, and returns quantile forecasts through POST /v1/forecast. CPU only. The code is MIT; the model weights have their own licence. urls: - https://github.com/mudler/timestral.cpp tags: - forecasting - time-series - CPU capabilities: default: cpu-timestral-cpp metal: metal-timestral-cpp uri: quay.io/go-skynet/local-ai-backends:latest-cpu-timestral-cpp mirrors: - localai/localai-backends:latest-cpu-timestral-cpp - name: cpu-timestral-cpp-development alias: timestral-cpp license: mit description: | timestral.cpp is a C++/ggml port of Mistral's Timestral time-series forecasting models. It takes numeric series, with optional covariates, and returns quantile forecasts through POST /v1/forecast. CPU only. The code is MIT; the model weights have their own licence. urls: - https://github.com/mudler/timestral.cpp tags: - forecasting - time-series - CPU capabilities: default: cpu-timestral-cpp metal: metal-timestral-cpp uri: quay.io/go-skynet/local-ai-backends:master-cpu-timestral-cpp mirrors: - localai/localai-backends:master-cpu-timestral-cpp - name: metal-timestral-cpp alias: timestral-cpp license: mit description: | timestral.cpp is a C++/ggml port of Mistral's Timestral time-series forecasting models. It takes numeric series, with optional covariates, and returns quantile forecasts through POST /v1/forecast. CPU only. The code is MIT; the model weights have their own licence. urls: - https://github.com/mudler/timestral.cpp tags: - forecasting - time-series - CPU capabilities: default: cpu-timestral-cpp metal: metal-timestral-cpp uri: quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-timestral-cpp mirrors: - localai/localai-backends:latest-metal-darwin-arm64-timestral-cpp - name: metal-timestral-cpp-development alias: timestral-cpp license: mit description: | timestral.cpp is a C++/ggml port of Mistral's Timestral time-series forecasting models. It takes numeric series, with optional covariates, and returns quantile forecasts through POST /v1/forecast. CPU only. The code is MIT; the model weights have their own licence. urls: - https://github.com/mudler/timestral.cpp tags: - forecasting - time-series - CPU capabilities: default: cpu-timestral-cpp metal: metal-timestral-cpp uri: quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-timestral-cpp mirrors: - localai/localai-backends:master-metal-darwin-arm64-timestral-cpp