GUI-Actor-3B-Qwen2.5-VL

microsoft/GUI-Actor-3B-Qwen2.5-VL

Image Text to Text3.8B parameterstransformersLicense: mit

Tracked by OpenModelStats since October 12, 2026View on Hugging Face ↗

Downloads 30D: 856
Total downloads: 17.9K
Gained 7D: —
Gained 30D: —
Likes: 14
Rank · tracked models: #38,298; 330(down 330 places)this week
Parameters: 3.8B
Last source update: Aug 9, 2025

It moved from #3644 to #3686 among tracked Image Text to Text models this week.

7D 30D 90D 1Y All

Total downloads Gained per day Rolling recent downloads

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

GUI-Actor-3B-Qwen2.5-VL is a image text to text model published by microsoft. OpenModelStats has tracked the model since Oct 12, 2026, most recently observing it Oct 27, 2026.

Published: Jun 1, 2025
Last updated: Aug 9, 2025
Library: transformers
License: mit
Task: Image Text to Text
Parameters: 3,787,653,120
Spaces: —
Derivative models: —
Velocity 7D/day: —

transformerssafetensorsqwen2_5_vlimage-text-to-textconversationalarxiv:2506.03143base_model:Qwen/Qwen2.5-VL-3B-Instructbase_model:finetune:Qwen/Qwen2.5-VL-3B-Instructlicense:miteval-resultstext-generation-inferenceendpoints_compatible

Publisher

microsoftView publisher statistics →

Derived from Qwen/Qwen2.5-VL-3B-Instruct (reported by the source; parent not yet tracked).

Similar models

Models similar to GUI-Actor-3B-Qwen2.5-VL
Model	Task	DL 30D	Likes	Params
HY-Embodied-0.5tencent	Image Text to Text	543	922	3.8B
Qwen3-VL-8B-Instruct-AWQ-8bitcyankiwi	Image Text to Text	479	4	3.8B
Qwen3-VL-8B-Thinking-AWQ-8bitcyankiwi	Image Text to Text	81	4	3.8B
Qwen2.5-VL-3B-InstructQwen	Image Text to Text	1.6M	737	3.8B
Qwen2.5-VL-3B-Instruct-AWQQwen	Image Text to Text	823.7K	77	3.8B
Nanonets-OCR2-3Bnanonets	Image Text to Text	230.4K	517	3.8B