From bfd6c09d88c1b967bc0b7529f3edd4433b423b04 Mon Sep 17 00:00:00 2001
From: "LocalAI [bot]" <139863280+localai-bot@users.noreply.github.com>
Date: Fri, 3 Jul 2026 18:02:09 +0200
Subject: [PATCH] chore(model gallery): :robot: add 1 new models via gallery
 agent (#10663)

chore(model gallery): :robot: add new models via gallery agent

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
---
 gallery/index.yaml | 52 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)

diff --git a/gallery/index.yaml b/gallery/index.yaml
index 61e4cf39e..a4147f318 100644
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -1,4 +1,56 @@
 ---
+- name: "qwopus3.6-35b-a3b-coder-mtp"
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  urls:
+    - https://huggingface.co/Jackrong/Qwopus3.6-35B-A3B-Coder-MTP-GGUF
+  description: |
+    # 🌟 Qwopus3.6-35B-A3B-v1
+
+    ## 💡 Base Model Overview
+
+    **Qwen3.6-35B-A3B** is an advanced hybrid sparse MoE (Mixture-of-Experts) model developed by Alibaba Cloud. It features 35B total parameters with only 3B active parameters per token, ensuring high inference efficiency. Architecturally, it combines Gated DeltaNet linear attention with standard gated attention layers, routing tokens across **256 experts**. It natively supports a massive **262k context window** and is specifically designed for high-performance agentic coding, deep reasoning, and multimodal tasks.
+
+    ## 🚀 Model Refinement & Logic Tuning （Qwopus3.6-35B-A3B-v1）
+
+    🪐**Qwopus3.6-35B-A3B-v1** is a reasoning-enhanced MoE (Mixture of Experts) model fine-tuned on top of **Qwen3.6-35B-A3B**.
+
+    ### 🛠 Training Strategy
+
+    The fine-tuning process for this model is structured into **three distinct stages of distributed SFT (Supervised Fine-Tuning)**, progressively scaling reasoning complexity and data diversity. This systematic approach ensures the model inherits the base MoE capabilities while sharpening its logic-handling depth.
+
+    ...
+  license: "apache-2.0"
+  tags:
+    - llm
+    - gguf
+    - vision
+    - multimodal
+  icon: https://cdn-uploads.huggingface.co/production/uploads/66309bd090589b7c65950665/ztbyGV_zGhzcLuTCSVyq3.png
+  overrides:
+    backend: llama-cpp
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    mmproj: llama-cpp/mmproj/Qwopus3.6-35B-A3B-Coder-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/Qwopus3.6-35B-A3B-Coder-MTP-Q4_K_M/Qwopus3.6-35B-A3B-Coder-MTP-Q4_K_M.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/Qwopus3.6-35B-A3B-Coder-MTP-Q4_K_M/Qwopus3.6-35B-A3B-Coder-MTP-Q4_K_M.gguf
+      sha256: c283cd2321a3cb4c6e7faf9481ac7d946913e4f02e20172eb2872112f567d8d4
+      uri: https://huggingface.co/Jackrong/Qwopus3.6-35B-A3B-Coder-MTP-GGUF/resolve/main/Qwopus3.6-35B-A3B-Coder-MTP-Q4_K_M.gguf
+    - filename: llama-cpp/mmproj/Qwopus3.6-35B-A3B-Coder-MTP-Q4_K_M/mmproj-F32.gguf
+      sha256: 5c82c8095717b39f29c88ebfec3607a10307785b1e14a87744603d6c582cd497
+      uri: https://huggingface.co/Jackrong/Qwopus3.6-35B-A3B-Coder-MTP-GGUF/resolve/main/mmproj-F32.gguf
 - name: "ornith-1.0-9b-mtp"
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls: