From 3f4e446adcdb517543c62d5f8e09ef7cdb5a14f5 Mon Sep 17 00:00:00 2001
From: localai-org-maint-bot <bot-opensource@localaisrl.com>
Date: Fri, 31 Jul 2026 23:05:02 +0200
Subject: [PATCH] gallery: add Qwopus3.6 27B Fusion variants (#11257)

Add Q4_K_M and Q8_0 llama.cpp entries for the newly released Qwopus3.6-27B Fusion reasoning and coding merge, with MTP enabled.

Assisted-by: Codex:gpt-5 [Hugging Face API]

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 2ba3f4b55..7c41c9dcc 100644
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -996,6 +996,74 @@
     - filename: llama-cpp/mmproj/Qwen3.6-27B-Fable-Fus-711-UnHeretic-NM-DAU-NEO-MAX-NEO-MTP-Q4_K_M/mmproj-F32.gguf
       sha256: fdc443e974cad1f61c45af1cfd5580855855ddce0d6c14cc500a5714c486ac1d
       uri: https://huggingface.co/DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF/resolve/main/mmproj-F32.gguf
+- &qwopus3-6-27b-fusion
+  name: "qwopus3.6-27b-fusion"
+  variants:
+    - model: qwopus3.6-27b-fusion-q8
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  urls:
+    - https://huggingface.co/Qwen/Qwen3.6-27B
+    - https://huggingface.co/KyleHessling1/Qwopus3.6-27B-Fusion-GGUF
+  description: |
+    Qwopus3.6-27B Fusion is an experimental 27B Qwen3.6 merge that combines the
+    Qwopus reasoning and coding fine-tunes. It targets agentic coding and
+    general reasoning, supports the Qwen3.6 262K context window, and retains
+    the base model's MTP head. This default entry uses the 16.8 GB Q4_K_M GGUF.
+  license: qwen
+  tags:
+    - llm
+    - gguf
+    - reasoning
+    - thinking
+    - mtp
+  overrides:
+    backend: llama-cpp
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    options:
+      - use_jinja:true
+      - spec_type:draft-mtp
+      - spec_n_max:6
+      - spec_p_min:0.75
+    parameters:
+      model: llama-cpp/models/Qwopus3.6-27B-Fusion-Q4_K_M/Qwopus3.6-27B-Fusion-Q4_K_M.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/Qwopus3.6-27B-Fusion-Q4_K_M/Qwopus3.6-27B-Fusion-Q4_K_M.gguf
+      sha256: 6d4e6e9ffba84ffe5166969303d4918f3a31682d75862416827412cee8f20d5d
+      uri: huggingface://KyleHessling1/Qwopus3.6-27B-Fusion-GGUF/Qwopus3.6-27B-Fusion-Q4_K_M.gguf
+- !!merge <<: *qwopus3-6-27b-fusion
+  name: "qwopus3.6-27b-fusion-q8"
+  variants: null
+  description: |
+    Qwopus3.6-27B Fusion in the higher-fidelity 29.0 GB Q8_0 GGUF format.
+    It retains the base model's MTP head for speculative decoding.
+  overrides:
+    backend: llama-cpp
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    options:
+      - use_jinja:true
+      - spec_type:draft-mtp
+      - spec_n_max:6
+      - spec_p_min:0.75
+    parameters:
+      model: llama-cpp/models/Qwopus3.6-27B-Fusion-Q8_0/Qwopus3.6-27B-Fusion-Q8_0.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/Qwopus3.6-27B-Fusion-Q8_0/Qwopus3.6-27B-Fusion-Q8_0.gguf
+      sha256: 5594e1776b75beedf4a54b933bba386dc83a0883417e3bcd9ef53fdfd120d5b6
+      uri: huggingface://KyleHessling1/Qwopus3.6-27B-Fusion-GGUF/Qwopus3.6-27B-Fusion-Q8_0.gguf
 - name: "minicpm5-1b-claude-opus-fable5-v2-thinking"
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls: