ScaleCUA-32B

OpenGVLab/ScaleCUA-32B

Image Text to Text33.5B parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since November 15, 2026View on Hugging Face ↗
Downloads 30D
1,818
Total downloads
3,303
Gained 7D
—
Gained 30D
—
Likes
22
Rank · tracked models
#27,782
5911(up 5911 places)this week
Parameters
33.5B
Last source update
Sep 18, 2025
  • It moved from #3071 to #2848 among tracked Image Text to Text models this week.

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Overview

ScaleCUA-32B is a image text to text model published by OpenGVLab. OpenModelStats has tracked the model since Nov 15, 2026, most recently observing it 2 min ago.

Published
Sep 16, 2025
Last updated
Sep 18, 2025
Library
transformers
License
apache-2.0
Task
Image Text to Text
Parameters
33,452,718,336
Spaces
—
Derivative models
—
Velocity 7D/day
—
transformerssafetensorsqwen2_5_vlimage-text-to-textagentconversationalendataset:OpenGVLab/ScaleCUA-Database_model:Qwen/Qwen2.5-VL-32B-Instructbase_model:finetune:Qwen/Qwen2.5-VL-32B-Instructlicense:apache-2.0eval-results

Publisher

OpenGVLabView publisher statistics →

Derived from Qwen/Qwen2.5-VL-32B-Instruct (reported by the source; parent not yet tracked).

Similar models

Models similar to ScaleCUA-32B
ModelDL 30D
Qwen2.5-VL-32B-Instruct-AWQQwen392.2K
Qwen2.5-VL-32B-InstructQwen360.8K
Lingshu-32Blingshu-medical-mllm1,829
Qwen2.5-VL-32B-Instructunsloth1,311
OpenCUA-32Bxlangai237
Qwen3-VL-32B-Instruct-FP8Qwen71.5K