hugpadhugpad

stepfun-ai / Step3-VL-10B-Base

Vision10B39952Updated Jan 29, 2026
Hugging Face

Downloads

399

Likes

52

Last updated

Jan 29, 2026

License

apache-2.0

STEP3-VL-10B is a lightweight open-source foundation model designed to redefine the trade-off between compact efficiency and frontier-level multimodal intelligence. Despite its compact 10B parameter footprint, STEP3-VL-10B excels in visual perception, complex reasoning, and hu…

Tasks & library

  • image text to text

Tags

  • step_robotics
  • image-text-to-text
  • custom_code

Technical specifications

Parameters10B
LibraryNot available
LanguagesNot available
Licenseapache-2.0