From cff69a05bf5242f79c9782300056685e740dc6dd Mon Sep 17 00:00:00 2001 From: localai-org-maint-bot Date: Sun, 2 Aug 2026 18:14:08 +0200 Subject: [PATCH] gallery: add Qwen3.6 27B Q8 variant (#11293) Assisted-by: Codex:gpt-5 Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com> --- gallery/index.yaml | 68 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 68 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index f423b6596..c337c5a09 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -4761,8 +4761,10 @@ variants: - model: qwen3.6-27b-dflash - model: qwen3.6-27b-nvfp4-mtp + - model: qwen3.6-27b-q8 url: github:mudler/LocalAI/gallery/virtual.yaml@master urls: + - https://huggingface.co/Qwen/Qwen3.6-27B - https://huggingface.co/unsloth/Qwen3.6-27B-GGUF description: | # Qwen3.6-27B @@ -4824,6 +4826,71 @@ - filename: llama-cpp/mmproj/Qwen3.6-27B-GGUF/mmproj-F32.gguf sha256: fdc443e974cad1f61c45af1cfd5580855855ddce0d6c14cc500a5714c486ac1d uri: https://huggingface.co/unsloth/Qwen3.6-27B-GGUF/resolve/main/mmproj-F32.gguf +- name: qwen3.6-27b-q8 + url: github:mudler/LocalAI/gallery/virtual.yaml@master + urls: + - https://huggingface.co/Qwen/Qwen3.6-27B + - https://huggingface.co/unsloth/Qwen3.6-27B-GGUF + description: | + # Qwen3.6-27B Q8_0 + + [](https://chat.qwen.ai) + + > [!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, KTransformers, etc. + + Following the February release of the Qwen3.5 series, we're pleased to share the first open-weight variant of Qwen3.6. Built on direct feedback from the community, Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience. + + ## Qwen3.6 Highlights + + This release delivers substantial upgrades, particularly in + + - **Agentic Coding:** the model now handles frontend workflows and repository-level reasoning with greater fluency and precision. + - **Thinking Preservation:** we've introduced a new option to retain reasoning context from historical messages, streamlining iterative development and reducing overhead. + + For more details, please refer to our blog post Qwen3.6-27B. + + ## Model Overview + + ... + license: apache-2.0 + icon: https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3.6/Figures/qwen3.6_27b_score.png + tags: + - llm + - gguf + - qwen + last_checked: "2026-04-30" + overrides: + backend: llama-cpp + function: + automatic_tool_parsing_fallback: true + grammar: + disable: true + known_usecases: + - chat + - vision + mmproj: llama-cpp/mmproj/Qwen3.6-27B-GGUF/mmproj-F32.gguf + options: + - use_jinja:true + parameters: + min_p: 0 + model: llama-cpp/models/Qwen3.6-27B-GGUF/Qwen3.6-27B-Q8_0.gguf + presence_penalty: 1.5 + repeat_penalty: 1 + temperature: 0.7 + top_k: 20 + top_p: 0.8 + template: + use_tokenizer_template: true + files: + - filename: llama-cpp/models/Qwen3.6-27B-GGUF/Qwen3.6-27B-Q8_0.gguf + sha256: f93f517f38e696d35a1a7df2c0e3155a64f4c4dcd662107a146ae263f7fb14ce + uri: https://huggingface.co/unsloth/Qwen3.6-27B-GGUF/resolve/main/Qwen3.6-27B-Q8_0.gguf + - filename: llama-cpp/mmproj/Qwen3.6-27B-GGUF/mmproj-F32.gguf + sha256: fdc443e974cad1f61c45af1cfd5580855855ddce0d6c14cc500a5714c486ac1d + uri: https://huggingface.co/unsloth/Qwen3.6-27B-GGUF/resolve/main/mmproj-F32.gguf - name: qwen3.6-35b-a3b-claude-4.6-opus-reasoning-distilled variants: - model: qwen3.6-35b-a3b-claude-4.6-opus-reasoning-distilled-apex-i-quality @@ -5048,6 +5115,7 @@ - model: qwen3.6-35b-a3b-apex-mtp-i-nano url: github:mudler/LocalAI/gallery/virtual.yaml@master urls: + - https://huggingface.co/Qwen/Qwen3.6-35B-A3B - https://huggingface.co/unsloth/Qwen3.6-35B-A3B-GGUF description: | # Qwen3.6-35B-A3B