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

gallery/index.yaml

@@ -3309,7 +3309,7 @@
     - gemma3
     - gemma-3
   overrides:
     #mmproj: gemma-3-27b-it-mmproj-f16.gguf
     parameters:
       model: gemma-3-27b-it-Q4_K_M.gguf
   files:
@@ -3327,7 +3327,7 @@
   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:
@@ -3345,7 +3345,7 @@
   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:
@@ -6963,7 +6963,7 @@
       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
@@ -23363,3 +23363,57 @@
     - filename: Qwen3-Grand-Horror-Light-1.7B.Q4_K_M.gguf
       sha256: cbbb0c5f6874130a8ae253377fdc7ad25fa2c1e9bb45f1aaad88db853ef985dc
       uri: huggingface://mradermacher/Qwen3-Grand-Horror-Light-1.7B-GGUF/Qwen3-Grand-Horror-Light-1.7B.Q4_K_M.gguf
+- !!merge <<: *qwen3vl
+  name: "qwen3-vl-8b-instruct"
+  urls:
+    - https://huggingface.co/Mungert/Qwen3-VL-8B-Instruct-GGUF
+  description: |
+    ### **Qwen3-VL-8B-Instruct**
+    *by Qwen Team (Hugging Face)*
+
+    A state-of-the-art vision-language model designed for rich multimodal understanding and reasoning. Built on a powerful architecture with **8 billion parameters**, Qwen3-VL-8B-Instruct excels in visual perception, spatial reasoning, and long-context multimodal tasks.
+
+    #### 🔍 **Key Features**:
+    - **256K native context length** (expandable to 1M), ideal for long documents, videos, and complex scenes.
+    - **Advanced spatial & video understanding** with precise object localization and timestamp-aware reasoning.
+    - **Strong multimodal reasoning** in STEM, logic, and real-world tasks—perfect for agent-based applications.
+    - **Visual coding support**: generates HTML/CSS/JS, Draw.io diagrams, and code from images.
+    - **High-precision OCR** across **32 languages**, including low-light, blurred, and ancient scripts.
+    - **Visual Agent** capability: interprets and interacts with GUIs, tools, and workflows.
+
+    #### 🛠️ **Architecture Highlights**:
+    - **Interleaved-MRoPE**: Enhanced positional encoding for better video and temporal reasoning.
+    - **DeepStack**: Fuses multi-level visual features for sharper image-text alignment.
+    - **Text–Timestamp Alignment**: Enables precise event localization in long videos.
+
+    #### 📌 **Use Cases**:
+    - Image/video captioning & analysis
+    - Visual question answering (VQA)
+    - Document understanding & extraction
+    - GUI automation & agent-based tasks
+    - Long-form content synthesis (books, research, video summaries)
+
+    #### 📚 **Citation**:
+    ```bibtex
+    @misc{qwen3technicalreport,
+      title={Qwen3 Technical Report},
+      author={Qwen Team},
+      year={2025},
+      eprint={2505.09388},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2505.09388}
+    }
+    ```
+
+    > ✅ **Official Hugging Face model**: [`Qwen/Qwen3-VL-8B-Instruct`](https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct)
+    > 🚀 **Try it live**: [Chat with Qwen3-VL](https://chat.qwenlm.ai/)
+
+    *Note: The GGUF version (Mungert/Qwen3-VL-8B-Instruct-GGUF) is a user-quantized variant and not the original model by the Qwen team.*
+  overrides:
+    parameters:
+      model: Qwen3-VL-8B-Instruct-q4_k_m.gguf
+  files:
+    - filename: Qwen3-VL-8B-Instruct-q4_k_m.gguf
+      sha256: a4d0b6e9d97ed31053fce7e2466c775ef39919bb86b1c56309b0e9089d540d45
+      uri: huggingface://Mungert/Qwen3-VL-8B-Instruct-GGUF/Qwen3-VL-8B-Instruct-q4_k_m.gguf