chore(model gallery): 🤖 add 1 new models via gallery agent

gallery/index.yaml

@@ -3295,7 +3295,7 @@
     - gemma3
     - gemma-3
   overrides:
     #mmproj: gemma-3-27b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-27b-it-Q4_K_M.gguf
   files:
@@ -3313,7 +3313,7 @@
   description: |
     google/gemma-3-12b-it is an open-source, state-of-the-art, lightweight, multimodal model built from the same research and technology used to create the Gemini models. It is capable of handling text and image input and generating text output. It has a large context window of 128K tokens and supports over 140 languages. The 12B variant has been fine-tuned using the instruction-tuning approach. Gemma 3 models are suitable for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes them deployable in environments with limited resources such as laptops, desktops, or your own cloud infrastructure.
   overrides:
     #mmproj: gemma-3-12b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-12b-it-Q4_K_M.gguf
   files:
@@ -3331,7 +3331,7 @@
   description: |
     Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. Gemma 3 models are multimodal, handling text and image input and generating text output, with open weights for both pre-trained variants and instruction-tuned variants. Gemma 3 has a large, 128K context window, multilingual support in over 140 languages, and is available in more sizes than previous versions. Gemma 3 models are well-suited for a variety of text generation and image understanding tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as laptops, desktops or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone. Gemma-3-4b-it is a 4 billion parameter model.
   overrides:
     #mmproj: gemma-3-4b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-4b-it-Q4_K_M.gguf
   files:
@@ -6949,7 +6949,7 @@
       sha256: 2756551de7d8ff7093c2c5eec1cd00f1868bc128433af53f5a8d434091d4eb5a
       uri: huggingface://Triangle104/Nano_Imp_1B-Q8_0-GGUF/nano_imp_1b-q8_0.gguf
 - &qwen25
   name: "qwen2.5-14b-instruct" ## Qwen2.5
   icon: https://avatars.githubusercontent.com/u/141221163
   url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
   license: apache-2.0
@@ -23023,3 +23023,37 @@
     - filename: Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-PKDick-V.i1-Q4_K_M.gguf
       sha256: 6955283520e3618fe349bb75f135eae740f020d9d7f5ba38503482e5d97f6f59
       uri: huggingface://mradermacher/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-PKDick-V-i1-GGUF/Qwen3-Yoyo-V4-42B-A3B-Thinking-TOTAL-RECALL-PKDick-V.i1-Q4_K_M.gguf
+- !!merge <<: *qwen25coder
+  name: "minimax-m2-i1"
+  urls:
+    - https://huggingface.co/mradermacher/MiniMax-M2-i1-GGUF
+  description: |
+    **MiniMax-M2** is a compact, high-performance MoE (Mixture of Experts) language model designed for elite coding and agent workflows. With **230 billion total parameters** and only **10 billion activated parameters**, it delivers frontier-level performance in coding, tool use, and agentic reasoning while maintaining fast inference, low latency, and cost efficiency.
+
+    ### 🔑 Key Features:
+    - **Top-tier Agent Performance**: Leads in benchmarks like BrowseComp, SWE-bench, and Terminal-Bench, excelling at long-horizon toolchains, multi-file edits, and test-validated fixes.
+    - **Open-Source & Deployable**: Released under the MIT license. Fully open for local deployment via vLLM, SGLang, MLX, and other frameworks.
+    - **Interleaved Thinking**: Uses a `<tool_call>...</tool_call>` format for internal reasoning—ensure this content is preserved in prompts for optimal behavior.
+    - **Designed for Efficiency**: Ideal for real-time agents, CI/CD pipelines, and scalable deployments with minimal infrastructure overhead.
+
+    ### 📊 Benchmark Highlights:
+    - **#1 Open-Source Model (AA Intelligence Score: 61)**
+    - **69.4% pass rate on SWE-bench Verified**
+    - **44% on BrowseComp** — unmatched among open models
+
+    ### 🛠️ Use Cases:
+    - Developer assistants, IDE bots, and terminal agents
+    - Automated testing, debugging, and code generation
+    - Long-context planning and complex task execution
+
+    > ✅ **Deploy it today**: https://huggingface.co/MiniMaxAI/MiniMax-M2
+    > 🚀 **Free for limited time**: [MiniMax Agent](https://agent.minimax.io/) | [API Platform](https://platform.minimax.io)
+
+    MiniMax-M2 proves that you don’t need a giant model to get max performance—**small, smart, and fast**.
+  overrides:
+    parameters:
+      model: MiniMax-M2.i1-Q4_K_M.gguf.part1of3
+  files:
+    - filename: MiniMax-M2.i1-Q4_K_M.gguf.part1of3
+      sha256: cb5a8b11a9cdaf3551e381772926e7188157f0fd50f25e07f0d3192537e92897
+      uri: huggingface://mradermacher/MiniMax-M2-i1-GGUF/MiniMax-M2.i1-Q4_K_M.gguf.part1of3