From 80893a298b4ccff1bd7fd7834051c30be1833087 Mon Sep 17 00:00:00 2001
From: "LocalAI [bot]" <139863280+localai-bot@users.noreply.github.com>
Date: Tue, 26 May 2026 22:02:12 +0200
Subject: [PATCH] chore(model gallery): :robot: add 1 new models via gallery
 agent (#10016)

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 | 64 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 64 insertions(+)

diff --git a/gallery/index.yaml b/gallery/index.yaml
index 96ca4e773..fcfa88120 100644
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -1,4 +1,68 @@
 ---
+- name: "qwopus3.5-9b-coder-mtp"
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  urls:
+    - https://huggingface.co/Jackrong/Qwopus3.5-9B-Coder-MTP-GGUF
+  description: |
+    # 🌟 Qwopus3.5-9B-v3.5
+
+    ## 💡 Model Overview & v3.5 Design
+
+    Qwopus3.5-9B-v3.5 is a **data-scaled continuation** of the Qwopus3.5-9B-v3 model.
+
+    The training data in v3.5 is expanded to cover a broader range of domains, including mathematics, programming, puzzle-solving, multilingual dialogue, instruction-following, multi-turn interactions, and STEM-related tasks.
+
+    Qwopus3.5-9B-v3.5 is a reasoning-enhanced model based on **Qwen3.5-9B**, designed for:
+
+      - 🧩 Structured reasoning
+      - 🔧 Tool-augmented workflows
+      - 🔁 Multi-step agentic tasks
+      - ⚡ Token-efficient inference
+
+    Compared with Qwopus3.5-9B-v3, **3.5 version does not introduce a new architecture, RL stage, or template redesign**.
+
+    This version is trained with approximately **2× more SFT data**.
+
+    ## 🎯 Motivation & Generalization Insight
+
+    The motivation behind v3.5 comes from a simple observation:
+
+    > This work is motivated by the hypothesis that scaling high-quality SFT data may further enhance the generalization ability of large language models.
+
+    In earlier Qwopus3.5 experiments, structured reasoning was observed to improve both **accuracy and efficiency**:
+
+    ...
+  license: "apache-2.0"
+  tags:
+    - llm
+    - gguf
+    - reasoning
+  icon: https://cdn-uploads.huggingface.co/production/uploads/66309bd090589b7c65950665/9EnS13MSxNU3snpAgEiLq.jpeg
+  overrides:
+    backend: llama-cpp
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    mmproj: llama-cpp/mmproj/Qwopus3.5-9B-Coder-MTP-GGUF/Qwopus3.5-9B-Coder-MTP-mmproj.gguf
+    options:
+      - use_jinja:true
+      - spec_type:draft-mtp
+      - spec_n_max:6
+      - spec_p_min:0.75
+    parameters:
+      model: llama-cpp/models/Qwopus3.5-9B-Coder-MTP-GGUF/Qwopus3.5-9B-Coder-MTP-Q4_K_M.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/Qwopus3.5-9B-Coder-MTP-GGUF/Qwopus3.5-9B-Coder-MTP-Q4_K_M.gguf
+      sha256: f6fc5d193045796d9e1870cbc40f827fe55f53f70593c3f5c1968b82b9331991
+      uri: https://huggingface.co/Jackrong/Qwopus3.5-9B-Coder-MTP-GGUF/resolve/main/Qwopus3.5-9B-Coder-MTP-Q4_K_M.gguf
+    - filename: llama-cpp/mmproj/Qwopus3.5-9B-Coder-MTP-GGUF/Qwopus3.5-9B-Coder-MTP-mmproj.gguf
+      sha256: f48daca405a1c768a9514e392c3955dcc4a9d66a5cf64cf45e064092b5f20ee4
+      uri: https://huggingface.co/Jackrong/Qwopus3.5-9B-Coder-MTP-GGUF/resolve/main/Qwopus3.5-9B-Coder-MTP-mmproj.gguf
 - name: "qwopus3.6-27b-v2-mtp"
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls: