From 5efd9ae8d7598315752f097df75f0a839f44c3dc Mon Sep 17 00:00:00 2001
From: mudler <2420543+mudler@users.noreply.github.com>
Date: Wed, 5 Nov 2025 14:33:35 +0000
Subject: [PATCH] chore(model gallery): :robot: add new models via gallery
 agent

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
---
 gallery/index.yaml | 42 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)

diff --git a/gallery/index.yaml b/gallery/index.yaml
index 209e4c6c83fb..cca6b2379cfb 100644
--- a/gallery/index.yaml
+++ b/gallery/index.yaml
@@ -23049,3 +23049,45 @@
     - 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"
+  urls:
+    - https://huggingface.co/mradermacher/Qwen3-VL-12B-Instruct-Brainstorm20x-GGUF
+  description: |
+    **Model Name:** Qwen3-VL-12B-Instruct-Brainstorm20x
+    **Base Model:** Qwen/Qwen3-VL-8B-Instruct
+    **Repository:** [mradermacher/Qwen3-VL-12B-Instruct-Brainstorm20x-GGUF](https://huggingface.co/mradermacher/Qwen3-VL-12B-Instruct-Brainstorm20x-GGUF)
+    **Model Type:** Multimodal Instruction-Tuned Vision-Language Model
+    **Architecture:** Qwen3-VL with Brainstorm 20x adapter (expanded to 12B parameters, 55 layers)
+    **Context Length:** Up to 256K tokens (extendable to 1M)
+    **Languages:** English (with strong multilingual OCR support)
+    **Key Features:**
+    - Advanced visual understanding: Recognizes objects, scenes, text, and spatial relationships with high precision.
+    - Long-form reasoning: Excels in complex, multi-step tasks including STEM, coding, and creative writing.
+    - Enhanced multimodal generation: Generates rich, detailed descriptions from images and videos; supports image-to-code (HTML/CSS/JS/Draw.io).
+    - Brainstorm 20x Enhancement: A proprietary adapter that significantly improves prose quality, coherence, emotional engagement, and creative depth—while maintaining strong instruction-following accuracy.
+    - Full support for long documents, books, and extended video analysis with second-level indexing.
+    - Integrates with GUI agents for PC/mobile task automation.
+
+    **Use Cases:**
+    - Creative writing, story generation, and narrative design
+    - Image and video analysis with rich contextual description
+    - Visual coding and interface design from screenshots
+    - Long-context reasoning and research
+    - AI-assisted brainstorming and ideation
+    - Advanced agent-based workflows
+
+    **Quantization Support:** GGUF (Q2_K to Q8_0), GPTQ, EXL2, AWQ, HQQ — with full support for **mmproj** quant (Q8, F16, BF16, F32) required for full functionality.
+
+    **Recommended Tools:** KoboldCpp, oobabooga/text-generation-webui, SillyTavern, or any GGUF-compatible inference engine.
+
+    **License:** Apache 2.0
+
+    > 📌 *Note: This is a fine-tuned, enhanced version of Qwen3-VL-8B-Instruct. The base model is officially released by Qwen. This variant includes the Brainstorm 20x expansion for deeper reasoning and richer output. Always use the full model with correct mmproj quantization for best results.*
+  overrides:
+    parameters:
+      model: Qwen3-VL-12B-Instruct-Brainstorm20x.Q4_K_S.gguf
+  files:
+    - filename: Qwen3-VL-12B-Instruct-Brainstorm20x.Q4_K_S.gguf
+      sha256: 42dbd1b00223c4d7030427ed4125c87329fc095ca9271826319148f8959dc875
+      uri: huggingface://mradermacher/Qwen3-VL-12B-Instruct-Brainstorm20x-GGUF/Qwen3-VL-12B-Instruct-Brainstorm20x.Q4_K_S.gguf