From 29347bad67eba359adae7934ad67e9c65d4f1350 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Fri, 11 Sep 2026 22:36:46 +0000 Subject: [PATCH] gallery: apply PR #11905 Assisted-by: localai-org-maint-bot:glm5.2 [gh] --- docs/content/features/model-gallery.md | 6 ++ gallery/index.yaml | 77 ++++++++++++++++++++------ 2 files changed, 65 insertions(+), 18 deletions(-) diff --git a/docs/content/features/model-gallery.md b/docs/content/features/model-gallery.md index e1763f163..50e0a2a3c 100644 --- a/docs/content/features/model-gallery.md +++ b/docs/content/features/model-gallery.md @@ -212,6 +212,12 @@ where: ### Model variants +For example, `qwopus3.8-27b-flash` offers Q4_K_M and Q8_0 GGUF builds +with llama.cpp MTP speculative decoding and the F32 vision projector. +Install `qwopus3.8-27b-flash-q8` directly to select Q8_0 explicitly. +Both builds use the embedded chat template. The publisher reports a known +Python code indentation issue. + Some gallery entries offer several builds of the same model: different quantizations, or the same weights served by a different engine. Such an entry carries a `variants` list, and installing it normally lets LocalAI choose: diff --git a/gallery/index.yaml b/gallery/index.yaml index f17899c19..ae0bc603d 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -47,24 +47,17 @@ sha256: "" uri: https://huggingface.co/unsloth/DeepSeek-V4-Flash-Vision-Exp-GGUF - name: "qwopus3.8-27b-flash" + variants: + - model: qwopus3.8-27b-flash-q8 url: "github:mudler/LocalAI/gallery/virtual.yaml@master" urls: + - https://huggingface.co/Jackrong/Qwopus3.8-27B-Flash - https://huggingface.co/Jackrong/Qwopus3.8-27B-Flash-GGUF description: | - # Qwen3.8-27B - - > [!Note] - > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. - > - > These artifacts are compatible with Hugging Face Transformers, vLLM, SGLang, TokenSpeed, etc. - - > [!Tip] - > For users seeking managed, scalable inference without infrastructure maintenance, the official Qwen API service is provided by Qwen Cloud. - > In particular, **Qwen3.8-27B** will be available as a hosted version with more production features, e.g., 1M context length by default, official built-in tools. For more information, please refer to the Qwen3.8-27B Overview. The service is coming soon. Stay tuned for updates. - - Following the widespread community adoption of the Qwen3.5 and Qwen3.6 series, we are pleased to introduce Qwen3.8, the most capable generation in the Qwen open-model family to date. - - ... + Qwopus3.8-27B-Flash is a Qwen3.8-27B fine-tune for reasoning and agent + workloads. This Q4_K_M GGUF includes the F32 vision projector and uses + llama.cpp's embedded chat template with MTP speculative decoding. + The publisher reports a known Python code indentation issue. license: "apache-2.0" tags: - llm @@ -75,6 +68,7 @@ - multimodal - instruction-tuned - reasoning + - mtp icon: https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3.5/demo/CI_Demo/mathv-1327.jpg overrides: backend: llama-cpp @@ -96,11 +90,58 @@ use_tokenizer_template: true files: - filename: llama-cpp/models/Qwopus3.8-27B-Flash-MTP-Q4_K_M/Qwopus3.8-27B-Flash-MTP-Q4_K_M.gguf - uri: https://huggingface.co/Jackrong/Qwopus3.8-27B-Flash-GGUF/resolve/main/Qwopus3.8-27B-Flash-MTP-Q4_K_M.gguf - sha256: 1b76ad1596d6afc0b6e38a2b45b404462920739bd3087960b7a18a74ca938a74 + sha256: 2b9a335bd33bb977d3127062061c12cc94f37ceef1850d372317fbf4ee89d9c5 + uri: https://huggingface.co/Jackrong/Qwopus3.8-27B-Flash-GGUF/resolve/e146d61e88782677805b3b68ad3adf8674dde80d/Qwopus3.8-27B-Flash-MTP-Q4_K_M.gguf - 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/main/mmproj-F32.gguf - sha256: 52e6818e4d18eea010c50e5245eaa10a8cc3dcc30efea4ff60cbad8abf5669e1 + sha256: be3f444ecaedf084fd19399ba18cefcbbe3789bb81f4ad5ed67c91a1a3f48a67 + uri: https://huggingface.co/Jackrong/Qwopus3.8-27B-Flash-GGUF/resolve/e146d61e88782677805b3b68ad3adf8674dde80d/mmproj-F32.gguf +- name: "qwopus3.8-27b-flash-q8" + url: "github:mudler/LocalAI/gallery/virtual.yaml@master" + urls: + - https://huggingface.co/Jackrong/Qwopus3.8-27B-Flash + - https://huggingface.co/Jackrong/Qwopus3.8-27B-Flash-GGUF + description: | + Qwopus3.8-27B-Flash is a Qwen3.8-27B fine-tune for reasoning and agent + workloads. This Q8_0 GGUF includes the F32 vision projector and uses + llama.cpp's embedded chat template with MTP speculative decoding. + The publisher reports a known Python code indentation issue. + license: "apache-2.0" + tags: + - llm + - gguf + - qwen + - qwen3 + - vision + - multimodal + - instruction-tuned + - reasoning + - mtp + icon: https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3.5/demo/CI_Demo/mathv-1327.jpg + overrides: + backend: llama-cpp + function: + automatic_tool_parsing_fallback: true + grammar: + disable: true + known_usecases: + - chat + mmproj: llama-cpp/mmproj/Qwopus3.8-27B-Flash-MTP-Q4_K_M/mmproj-F32.gguf + options: + - use_jinja:true + - spec_type:draft-mtp + - spec_n_max:6 + - spec_p_min:0.75 + parameters: + model: llama-cpp/models/Qwopus3.8-27B-Flash-MTP-Q8_0/Qwopus3.8-27B-Flash-MTP-Q8_0.gguf + template: + use_tokenizer_template: true + files: + - filename: llama-cpp/models/Qwopus3.8-27B-Flash-MTP-Q8_0/Qwopus3.8-27B-Flash-MTP-Q8_0.gguf + sha256: a97de033ea60066a1941fe4dfb2e631b390cbc7c7563cea2446b7f08065228ec + uri: https://huggingface.co/Jackrong/Qwopus3.8-27B-Flash-GGUF/resolve/e146d61e88782677805b3b68ad3adf8674dde80d/Qwopus3.8-27B-Flash-MTP-Q8_0.gguf + - filename: llama-cpp/mmproj/Qwopus3.8-27B-Flash-MTP-Q4_K_M/mmproj-F32.gguf + sha256: be3f444ecaedf084fd19399ba18cefcbbe3789bb81f4ad5ed67c91a1a3f48a67 + uri: https://huggingface.co/Jackrong/Qwopus3.8-27B-Flash-GGUF/resolve/e146d61e88782677805b3b68ad3adf8674dde80d/mmproj-F32.gguf - name: "qwen3.8-27b" url: "github:mudler/LocalAI/gallery/virtual.yaml@master" urls: