chore(model gallery): 🤖 add 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
@@ -22079,3 +22079,31 @@
     - filename: Tlacuilo-12B.i1-Q4_K_M.gguf
       sha256: 94218112aa02113c8e21cd2c1d10818bea39bc6aee7e67be6014f86e80e76cb1
       uri: huggingface://mradermacher/Tlacuilo-12B-i1-GGUF/Tlacuilo-12B.i1-Q4_K_M.gguf
+- !!merge <<: *qwen3
+  name: "capybara-instruct-8b"
+  urls:
+    - https://huggingface.co/mradermacher/capybara-instruct-8b-GGUF
+  description: |
+    **Model Name:** Qwen3-8B (Base Model)
+    **Repository:** [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B)
+    **License:** Apache 2.0
+    **Description:**
+    Qwen3-8B is a state-of-the-art 8.2-billion-parameter dense language model from Alibaba's Qwen series, designed for advanced reasoning, instruction following, and multilingual tasks. It uniquely supports seamless switching between **thinking mode** (for complex logic, math, and coding) and **non-thinking mode** (for efficient dialogue), enabling optimal performance across diverse use cases. Built with extensive training and optimized for both reasoning and conversational fluency, it excels in agent-based tasks, creative writing, and long-context processing (up to 131,072 tokens with YaRN scaling).
+
+    **Key Features:**
+    - 8.2B parameters, 36 layers, GQA with 32 Q & 8 KV heads
+    - Native support for 32K tokens, up to 131K with YaRN scaling
+    - Dual-mode operation: thinking (reasoning) and non-thinking (dialogue)
+    - Strong multilingual support (100+ languages)
+    - Optimized for deployment via vLLM, SGLang, llama.cpp, and more
+
+    **Best For:** Advanced reasoning, agent workflows, multilingual applications, and high-performance inference.
+
+    > *Note: The model at `mradermacher/capybara-instruct-8b-GGUF` is a quantized and fine-tuned version of this base model.*
+  overrides:
+    parameters:
+      model: capybara-instruct-8b.Q4_K_M.gguf
+  files:
+    - filename: capybara-instruct-8b.Q4_K_M.gguf
+      sha256: 6b12a3db63f46f6267ff7bf90e29079060dba84427932ea596cf73277c8e9612
+      uri: huggingface://mradermacher/capybara-instruct-8b-GGUF/capybara-instruct-8b.Q4_K_M.gguf