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

gallery/index.yaml

@@ -3127,7 +3127,7 @@
     - gemma3
     - gemma-3
   overrides:
     #mmproj: gemma-3-27b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-27b-it-Q4_K_M.gguf
   files:
@@ -3145,7 +3145,7 @@
   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:
@@ -3163,7 +3163,7 @@
   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:
@@ -6781,7 +6781,7 @@
       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
@@ -22950,3 +22950,41 @@
     - filename: apollo-astralis-4b.i1-Q4_K_M.gguf
       sha256: 94e1d371420b03710fc7de030c1c06e75a356d9388210a134ee2adb4792a2626
       uri: huggingface://mradermacher/apollo-astralis-4b-i1-GGUF/apollo-astralis-4b.i1-Q4_K_M.gguf
+- !!merge <<: *qwen3
+  name: "qwen3-4b"
+  urls:
+    - https://huggingface.co/mrgoldengun/Qwen3-4B-Q2_K-GGUF
+  description: |
+    **Model Name:** Qwen3-4B
+    **Type:** Causal Language Model (LLM)
+    **Size:** 4.0 billion parameters
+    **Architecture:** Dense, with support for both **thinking mode** (for complex reasoning, math, coding) and **non-thinking mode** (for efficient dialogue) within a single model.
+
+    ### Key Features:
+    - **Dual-mode reasoning**: Seamlessly switch between deep thinking (for logic, math, code) and fast, conversational mode.
+    - **Advanced reasoning & instruction-following**: Outperforms previous Qwen models in logical reasoning, coding, and creative tasks.
+    - **Strong agent capabilities**: Excellent at tool integration and complex task execution.
+    - **Multilingual support**: Trained on 100+ languages and dialects with robust translation and instruction-following abilities.
+    - **Extended context**: Native support for up to **32,768 tokens**, extendable to **131,072 tokens** using YaRN RoPE scaling.
+
+    ### Use Cases:
+    - Complex problem solving (math, programming)
+    - Long-form content generation
+    - Multilingual chat and dialogue
+    - Agent-based workflows with tool use
+
+    ### Ideal For:
+    Researchers, developers, and enterprises needing a lightweight yet powerful LLM with advanced reasoning and agentic behavior.
+
+    > 🔗 **Official Repository**: [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B)
+    > 📚 **Documentation & Blog**: [qwenlm.github.io](https://qwenlm.github.io)
+    > 🧠 **Try it live**: [Qwen Chat](https://chat.qwen.ai)
+
+    *Note: This model is the original, non-quantized version. The GGUF quantized variant (e.g., `mrgoldengun/Qwen3-4B-Q2_K-GGUF`) is a conversion for efficient local inference but may have reduced precision.*
+  overrides:
+    parameters:
+      model: qwen3-4b-q2_k.gguf
+  files:
+    - filename: qwen3-4b-q2_k.gguf
+      sha256: cc350afd5f4f2210cd11283f44c3d3b5c0892b32afc6ac89288114eaf650ef48
+      uri: huggingface://mrgoldengun/Qwen3-4B-Q2_K-GGUF/qwen3-4b-q2_k.gguf