Step3-VL-10B

stepfun-ai/Step3-VL-10B

Image Text to Text10.2B parametersLicense: apache-2.0
Tracked by OpenModelStats since September 7, 2026View on Hugging Face ↗
Downloads 30D
27.5K
Total downloads
1.9M
Gained 7D
+11.6K(increase)
0.6%(up) vs baseline
Gained 30D
—
Likes
417
+1 in 7D
Rank · tracked models
#5,000
16(up 16 places)this week
Parameters
10.2B
Last source update
Feb 4, 2026
Momentum
80.3
  • Step3-VL-10B gained 11.6K downloads during the last seven tracked days.
  • It moved from #636 to #629 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

Step3-VL-10B is a image text to text model published by stepfun-ai. OpenModelStats has tracked the model since Sep 7, 2026, most recently observing it 32h ago.

Published
Jan 13, 2026
Last updated
Feb 4, 2026
Library
—
License
apache-2.0
Task
Image Text to Text
Parameters
10,171,750,144
Spaces
—
Derivative models
2
Velocity 7D/day
1,651
safetensorsstep_roboticsimage-text-to-textconversationalcustom_codearxiv:2601.09668base_model:stepfun-ai/Step3-VL-10B-Basebase_model:finetune:stepfun-ai/Step3-VL-10B-Baselicense:apache-2.0region:us

Model family

Based on base-model relationships reported by the source's metadata.

Similar models

Models similar to Step3-VL-10B
ModelDL 30D
Step3-VL-10B-Basestepfun-ai325
Huihui-Step3-VL-10B-abliteratedhuihui-ai127
Ovis1.6-Gemma2-9BATH-MaaS4,608
GLM-4.1V-9B-Thinkingzai-org168.2K
GLM-4.6V-Flashzai-org108.9K
GLM-4.1V-9B-Basezai-org789
stepfun-ai/Step3-VL-10B — Downloads, Growth & Stats | OpenModelStats