ScaleCUA-3B

OpenGVLab/ScaleCUA-3B

Image Text to Text3.8B parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since November 15, 2026View on Hugging Face ↗
Downloads 30D
1,821
Total downloads
6,094
Gained 7D
—
Gained 30D
—
Likes
13
Rank · tracked models
#27,705
5985(up 5985 places)this week
Parameters
3.8B
Last source update
Sep 17, 2025
  • It moved from #3073 to #2842 among tracked Image Text to Text models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

ScaleCUA-3B is a image text to text model published by OpenGVLab. OpenModelStats has tracked the model since Nov 15, 2026, most recently observing it 6 min ago.

Published
Sep 16, 2025
Last updated
Sep 17, 2025
Library
transformers
License
apache-2.0
Task
Image Text to Text
Parameters
3,754,622,976
Spaces
—
Derivative models
—
Velocity 7D/day
—
transformerssafetensorsqwen2_5_vlimage-text-to-textagentconversationalendataset:OpenGVLab/ScaleCUA-Database_model:Qwen/Qwen2.5-VL-3B-Instructbase_model:finetune:Qwen/Qwen2.5-VL-3B-Instructlicense:apache-2.0text-generation-inference

Publisher

OpenGVLabView publisher statistics →

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

Similar models

Models similar to ScaleCUA-3B
ModelDL 30D
Qwen2.5-VL-3B-InstructQwen1.9M
Nanonets-OCR2-3Bnanonets895.5K
Qwen2.5-VL-3B-Instruct-AWQQwen849.8K
typhoon-ocr-3btyphoon-ai40.7K
Qwen2.5-VL-3B-Instruct-abliteratedhuihui-ai22.2K
Qwen2.5-VL-3B-Instruct-4bitmlx-community6,596