diff --git a/docs/content/features/model-gallery.md b/docs/content/features/model-gallery.md index 770428d57..7baa18087 100644 --- a/docs/content/features/model-gallery.md +++ b/docs/content/features/model-gallery.md @@ -39,6 +39,20 @@ Both views use the same model selection and store the view, search, filter, and selection in the URL. Installing from Explore does not move you away from the catalog; the entry updates in place when the operation finishes. +## Hemmingway-1 + +Install `hemmingway-1` for English text generation with llama.cpp. The gallery groups its Q4_K_M and Q8_0 builds as variants. +To select a specific build, use `local-ai models install hemmingway-1 --variant hemmingway-1-q8` for Q8_0. +The configurations default to 32,768 context tokens. Increase the context size only if available memory permits. +The [model license](https://huggingface.co/Altworld/Hemmingway-1) is CC BY-NC 4.0; commercial use requires a separate agreement. + +## Qwen-Image 2.1 + +For image generation, install `qwen-image-2.1-q4_k-ggml` or its `qwen-image-2.1-q8_0-ggml` variant. +These entries use `stablediffusion-ggml` and include the text encoder, vision projector, and VAE. +The invalid `qwen-image-2.1-uncensored` chat entry was removed because llama.cpp cannot load its diffusion weights. +This removal does not delete previously installed models. Remove that configuration before installing an image-generation entry. + ## VRAM and download size estimates When browsing the gallery or importing a model by URI, LocalAI can show **estimated download size** and **estimated VRAM** for models. diff --git a/gallery/index.yaml b/gallery/index.yaml index 6fb53a544..d5419f747 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -1,33 +1,4 @@ --- -- name: "qwen-image-2.1-uncensored" - url: "github:mudler/LocalAI/gallery/virtual.yaml@master" - urls: - - https://huggingface.co/abenzerps/Qwen-Image-2.1-Uncensored-GGUF - description: "\U0001F916 ModelScope  |\n  \U0001F917 HuggingFace  |\n  \U0001F4D1 Blog  |\n  \U0001F5A5️ Demo  |\n  \U0001FAE8 Discord  |\n  \U0001F4AC WeChat\n\n## Introduction\n\nWe are excited to open-source **Qwen-Image-2.1**, a unified text-to-image generation and image editing model in the Qwen family. With just **7B parameters in its visual generation component** (32 Single-Stream DiT layers), Qwen-Image-2.1 balances generation quality, inference efficiency, and versatility.\n\nFour key improvements define this release:\n\n...\n" - license: "other" - tags: - - llm - - gguf - - qwen - icon: https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/image2.1/logo.png - overrides: - backend: llama-cpp - function: - automatic_tool_parsing_fallback: true - grammar: - disable: true - known_usecases: - - chat - options: - - use_jinja:true - parameters: - model: llama-cpp/models/qwen-image-2.1-UC-Q4_K_M/qwen-image-2.1-UC-Q4_K_M.gguf - template: - use_tokenizer_template: true - files: - - filename: llama-cpp/models/qwen-image-2.1-UC-Q4_K_M/qwen-image-2.1-UC-Q4_K_M.gguf - sha256: e79c8a009f2ecbdb6c70fd663d9aea9ee304a0d91f347e4169a756b8ad141b41 - uri: https://huggingface.co/abenzerps/Qwen-Image-2.1-Uncensored-GGUF/resolve/main/qwen-image-2.1-UC-Q4_K_M.gguf - name: "ornith-1.5-9b-uncensored" url: "github:mudler/LocalAI/gallery/virtual.yaml@master" urls: @@ -331,6 +302,74 @@ - filename: llama-cpp/mmproj/Qwopus3.8-27B-Flash-MTP-Q4_K_M/mmproj-F32.gguf uri: https://huggingface.co/Jackrong/Qwopus3.8-27B-Flash-GGUF/resolve/e146d61e88782677805b3b68ad3adf8674dde80d/mmproj-F32.gguf sha256: 52e6818e4d18eea010c50e5245eaa10a8cc3dcc30efea4ff60cbad8abf5669e1 +- name: hemmingway-1 + variants: + - model: hemmingway-1-q8 + url: "github:mudler/LocalAI/gallery/virtual.yaml@master" + urls: + - https://huggingface.co/Altworld/Hemmingway-1 + - https://huggingface.co/mradermacher/Hemmingway-1-GGUF + description: | + Hemmingway-1 is Altworld's English-first 27B text model, fine-tuned from Qwen3.8-27B for everyday messages and creative writing. + This Q4_K_M GGUF build uses llama.cpp and the model's embedded chat template. Licensed under CC BY-NC 4.0; commercial use requires a separate agreement. + license: cc-by-nc-4.0 + tags: + - llm + - gguf + - cpu + - gpu + - text-generation + - creative-writing + - qwen + last_checked: "2026-09-26" + overrides: + backend: llama-cpp + context_size: 32768 + known_usecases: + - chat + options: + - use_jinja:true + template: + use_tokenizer_template: true + parameters: + model: Hemmingway-1.Q4_K_M.gguf + files: + - filename: Hemmingway-1.Q4_K_M.gguf + sha256: d8a77565035547f39388969e1ef0e83f646f366e7bdef1e1ce63ad0b0d785dbc + uri: huggingface://mradermacher/Hemmingway-1-GGUF/Hemmingway-1.Q4_K_M.gguf +- name: hemmingway-1-q8 + url: "github:mudler/LocalAI/gallery/virtual.yaml@master" + urls: + - https://huggingface.co/Altworld/Hemmingway-1 + - https://huggingface.co/mradermacher/Hemmingway-1-GGUF + description: | + Hemmingway-1 is Altworld's English-first 27B text model, fine-tuned from Qwen3.8-27B for everyday messages and creative writing. + This Q8_0 GGUF build uses llama.cpp and the model's embedded chat template. Licensed under CC BY-NC 4.0; commercial use requires a separate agreement. + license: cc-by-nc-4.0 + tags: + - llm + - gguf + - cpu + - gpu + - text-generation + - creative-writing + - qwen + last_checked: "2026-09-26" + overrides: + backend: llama-cpp + context_size: 32768 + known_usecases: + - chat + options: + - use_jinja:true + template: + use_tokenizer_template: true + parameters: + model: Hemmingway-1.Q8_0.gguf + files: + - filename: Hemmingway-1.Q8_0.gguf + sha256: 10b566343db6905215c2d635285ffb43ada05a2f9b1e8e85562c8e366fac1809 + uri: huggingface://mradermacher/Hemmingway-1-GGUF/Hemmingway-1.Q8_0.gguf - name: "qwen3.8-27b" url: "github:mudler/LocalAI/gallery/virtual.yaml@master" urls: