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

@@ -22938,3 +22938,28 @@
     - filename: ReForm-32B.i1-Q4_K_M.gguf
       sha256: a7f69d6e2efe002368bc896fc5682d34a1ac63669a4db0f42faf44a29012dc3f
       uri: huggingface://mradermacher/ReForm-32B-i1-GGUF/ReForm-32B.i1-Q4_K_M.gguf
+- !!merge <<: *qwen3vl
+  name: "gelato-30b-a3b"
+  urls:
+    - https://huggingface.co/noctrex/Gelato-30B-A3B-GGUF
+  description: |
+    **Gelato-30B-A3B** is a state-of-the-art vision-language model specifically designed for GUI computer-use tasks, such as precise UI element localization and interaction. Built on the **Qwen3-VL-30B-A3B-Instruct** foundation, it was fine-tuned on the large-scale **Click-100k** dataset, which captures real-world user interactions with graphical interfaces.
+
+    Key Features:
+    - **High Accuracy**: Achieves **63.88%** on ScreenSpot-Pro and **73.40%** on OS-World-G, outperforming prior specialized models and larger VLMs.
+    - **Efficient Inference**: With only **3.3 GB activated memory**, it delivers strong performance on low-resource setups.
+    - **Open Source & Accessible**: Fully open-source under the Apache 2.0 license, enabling research and deployment in agentic systems.
+    - **Application Ready**: Designed for use in AI agents that interact with desktop GUIs—ideal for automation, assistive technologies, and human-computer interaction research.
+
+    Use Case: Perfect for building AI agents that understand and interact with software interfaces by interpreting visual cues and user instructions.
+
+    👉 **Model**: [mlfoundations-cua-dev/Gelato-30B-A3B](https://huggingface.co/mlfoundations-cua-dev/Gelato-30B-A3B)
+    👉 **Dataset**: [Click-100k](https://huggingface.co/datasets/mlfoundations/clicks-100k)
+    👉 **Training & Evaluation**: [GitHub Repo](https://github.com/mlfoundations/grounding-model-os-world)
+  overrides:
+    parameters:
+      model: Gelato-30B-A3B-Q4_K_M.gguf
+  files:
+    - filename: Gelato-30B-A3B-Q4_K_M.gguf
+      sha256: d44af330b10adaa291dced867ae90bbbdc8d502f97d994d7209828efe6343824
+      uri: huggingface://noctrex/Gelato-30B-A3B-GGUF/Gelato-30B-A3B-Q4_K_M.gguf