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

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

Author: mudler

gallery/index.yaml

@@ -23363,3 +23363,29 @@
     - 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: "qwen.qwen3-vl-235b-a22b-thinking"
+  urls:
+    - https://huggingface.co/DevQuasar/Qwen.Qwen3-VL-235B-A22B-Thinking-GGUF
+  description: |
+    The **Qwen3-VL-235B-A22B-Thinking** is a large multimodal language model developed by Alibaba Cloud as part of the Qwen series. It is a 235-billion-parameter variant designed for advanced reasoning and multimodal understanding, capable of processing both text and images. This model excels in complex tasks such as visual question answering, image captioning, reasoning over visual content, and long-form text generation with deep contextual awareness.
+
+    Key features:
+    - **Multimodal capability**: Integrates vision and language models to interpret and reason over images and text.
+    - **Advanced reasoning**: Built with a “Thinking” architecture that enables step-by-step reasoning, improving performance on logic, math, and complex problem-solving tasks.
+    - **Large-scale training**: Trained on vast amounts of diverse data, enabling strong generalization and robustness across domains.
+    - **High accuracy and coherence**: Delivers fluent, factually consistent, and contextually relevant outputs.
+
+    This model is ideal for research, AI assistants, content creation, and any application requiring deep understanding of visual and textual information.
+
+    > 🔗 Base model: [Qwen/Qwen3-VL-235B-A22B-Thinking](https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Thinking)
+    > 📦 Repository: [DevQuasar/Qwen.Qwen3-VL-235B-A22B-Thinking-GGUF](https://huggingface.co/DevQuasar/Qwen.Qwen3-VL-235B-A22B-Thinking-GGUF) — a quantized GGUF version for efficient local inference.
+
+    Note: The version on Hugging Face (DevQuasar) is a quantized GGUF format for local deployment; the original, full-precision model is maintained by Alibaba's Qwen team.
+  overrides:
+    parameters:
+      model: Qwen.Qwen3-VL-235B-A22B-Thinking.Q4_K_M-00001-of-00011.gguf
+  files:
+    - filename: Qwen.Qwen3-VL-235B-A22B-Thinking.Q4_K_M-00001-of-00011.gguf
+      sha256: 246cda7f9e1f173fc57310e9bdbef86883f9989f69391a76fd41ec1b48d39f97
+      uri: huggingface://DevQuasar/Qwen.Qwen3-VL-235B-A22B-Thinking-GGUF/Qwen.Qwen3-VL-235B-A22B-Thinking.Q4_K_M-00001-of-00011.gguf