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
@@ -23049,3 +23049,63 @@
     - filename: YanoljaNEXT-Rosetta-27B-2511.i1-Q4_K_M.gguf
       sha256: 0a599099e93ad521045e17d82365a73c1738fff0603d6cb2c9557e96fbc907cb
       uri: huggingface://mradermacher/YanoljaNEXT-Rosetta-27B-2511-i1-GGUF/YanoljaNEXT-Rosetta-27B-2511.i1-Q4_K_M.gguf
+- !!merge <<: *qwen3vl
+  name: "qwen3-vl-12b-instruct-brainstorm20x-i1"
+  urls:
+    - https://huggingface.co/mradermacher/Qwen3-VL-12B-Instruct-Brainstorm20x-i1-GGUF
+  description: |
+    **Model Name:** Qwen3-VL-12B-Instruct-Brainstorm20x
+    **Base Model:** Qwen/Qwen3-VL-8B-Instruct
+    **Repository:** [mradermacher/Qwen3-VL-12B-Instruct-Brainstorm20x-i1-GGUF](https://huggingface.co/mradermacher/Qwen3-VL-12B-Instruct-Brainstorm20x-i1-GGUF)
+    **Type:** Multimodal Instruction-Finetuned Language Model (Vision-Language)
+    **Architecture:** Qwen3-VL with Brainstorm 20x adapter (expanded from 8B to 12B, 55 layers, 608 tensors)
+
+    ---
+
+    ### 🔍 **Overview**
+    A powerful, instruction-tuned multimodal model that combines **Qwen3-VL-8B-Instruct** with the advanced **Brainstorm 20x adapter**, enhancing reasoning, creativity, and narrative depth. This model excels at image-to-text generation, visual coding, long-context understanding (up to 256K tokens), and complex multimodal tasks.
+
+    ---
+
+    ### 🌟 **Key Features**
+    - **Enhanced Creative Reasoning:** Brainstorm 20x improves prose quality, coherence, emotional engagement, and detail density—ideal for storytelling, brainstorming, and creative writing.
+    - **Stronger Visual Understanding:** Superior object recognition, spatial reasoning, video comprehension, and OCR (supports 32 languages).
+    - **Code & Image Generation:** Generates HTML/CSS/JS, Draw.io diagrams, and structured code from images.
+    - **Long-Context & Multimodal Flexibility:** Handles books, videos, and detailed prompts with full recall and temporal indexing.
+    - **Highly Customizable:** Works with GGUF, GPTQ, EXL2, AWQ, and HQQ quantizations; requires a separate `mmproj` quant (Q8/F16/BF16/F32) for full functionality.
+
+    ---
+
+    ### 🛠️ **Use Cases**
+    - Creative writing & world-building
+    - Visual brainstorming & ideation
+    - AI-powered design & coding from images
+    - Long-form content generation
+    - Multimodal agents and GUI interaction
+
+    ---
+
+    ### ⚙️ **Recommended Settings**
+    - **Temperature:** 0.3–0.7 (up to 1.5 for creative tasks)
+    - **Top-p:** 0.8, **Top-k:** 20
+    - **Repetition Penalty:** 1.05–1.1
+    - **Smoothing Factor:** 1.5 (in KoboldCpp, oobabooga, SillyTavern)
+    - **Context Length:** At least 8K for complex tasks
+
+    ---
+
+    ### 📌 **Note on Quantization**
+    This repository contains **quantized GGUF versions** of the model. The original full-precision base model is **Qwen/Qwen3-VL-8B-Instruct**. To access the true base model description and weights, refer to the original repo: [Qwen/Qwen3-VL-8B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct).
+
+    ---
+
+    **Ideal for:** Developers, creators, researchers, and AI enthusiasts seeking a rich, expressive, and deeply reasoning multimodal model with exceptional narrative and visual intelligence.
+
+    > ✅ **Use the original base model for full precision; use this GGUF version for efficient, high-quality inference.**
+  overrides:
+    parameters:
+      model: Qwen3-VL-12B-Instruct-Brainstorm20x.i1-Q4_K_M.gguf
+  files:
+    - filename: Qwen3-VL-12B-Instruct-Brainstorm20x.i1-Q4_K_M.gguf
+      sha256: 1d960b389b00e064864a2e835daaafb02026961c85ce45473d12b42f18f5a263
+      uri: huggingface://mradermacher/Qwen3-VL-12B-Instruct-Brainstorm20x-i1-GGUF/Qwen3-VL-12B-Instruct-Brainstorm20x.i1-Q4_K_M.gguf