ibm-granite / granite-vision-3.2-2b

Vision3B2.8K126Updated Apr 2, 2026

Downloads

2.8K

Likes

126

Last updated

Apr 2, 2026

License

apache-2.0

Model Summary: granite-vision-3.2-2b is a compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more. The model was trained on a meticu…

Tasks & library

  • image text to text
  • transformers

Tags

  • transformers
  • llava_next
  • image-text-to-text
  • conversational
  • en

Technical specifications

Parameters3B
Librarytransformers
Languagesen
Licenseapache-2.0