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
@@ -22192,3 +22192,31 @@
     - filename: VerbaMaxima-12B.i1-Q4_K_M.gguf
       sha256: 106040cc375b063b225ae359c5d62893f4699dfd9c33d241cacc6dfe529fa13d
       uri: huggingface://mradermacher/VerbaMaxima-12B-i1-GGUF/VerbaMaxima-12B.i1-Q4_K_M.gguf
+- !!merge <<: *llama32
+  name: "llama3.2-coldbrew-4x3b-argon-test1-q5_k_m"
+  urls:
+    - https://huggingface.co/Theros/Llama3.2-ColdBrew-4x3B-Argon-test1-Q5_K_M-GGUF
+  description: |
+    **Model Name:** Llama3.2-ColdBrew-4x3B-Argon-test1
+    **Type:** Mixture of Experts (MoE) Large Language Model
+    **Base Architecture:** Llama 3.2 (3B parameter models)
+    **Repository:** [SvalTek/Llama3.2-ColdBrew-4x3B-Argon-test1](https://huggingface.co/SvalTek/Llama3.2-ColdBrew-4x3B-Argon-test1)
+
+    **Description:**
+    Llama3.2-ColdBrew-4x3B-Argon-test1 is a specialized **Mixture of Experts (MoE)** model built by merging four distinct 3B-parameter Llama 3.2-based models using **LazyMergekit**. It dynamically routes inputs to specialized expert sub-models based on content, enabling high performance across diverse tasks:
+
+    - **Bronze Expert:** Optimized for **tools & programming** (code generation, debugging, API usage).
+    - **Sage Expert:** Focused on **creative writing, roleplay, and storytelling**.
+    - **Oracle Expert:** Designed for **general knowledge, facts, and Q&A**.
+    - **OverThinker Expert:** Specialized in **reasoning, step-by-step analysis, and introspection**.
+
+    Each expert is activated via context-aware prompting, making the model highly efficient and accurate for specific use cases. The model supports both standard inference and integration via `transformers` or `llama.cpp`.
+
+    **Use Case:** Ideal for applications requiring fine-grained, task-specific intelligence—such as code assistants, narrative generation, technical Q&A, or complex reasoning—without the overhead of a single monolithic large model.
+
+    **Quantized Version:** Available in GGUF format (e.g., `Theros/Llama3.2-ColdBrew-4x3B-Argon-test1-Q5_K_M-GGUF`) for local inference via llama.cpp.
+
+    > ✅ **Note:** This model is *not* a direct release from Meta. It is a community-created merge of multiple specialized models. Always refer to the original repository for full context and licensing.
+  overrides:
+    parameters:
+      model: Theros/Llama3.2-ColdBrew-4x3B-Argon-test1-Q5_K_M-GGUF