hugpadhugpad

ibm-granite / granite-4.0-3b-vision

Vision4B45.9K113Updated Apr 30, 2026
Hugging Face

Downloads

45.9K

Likes

113

Last updated

Apr 30, 2026

License

apache-2.0

Model Summary: Granite-4.0-3B-Vision is a vision-language model (VLM) designed for enterprise-grade document data extraction. It focuses on specialized, complex extraction tasks that ultracompact models often struggle with:

Tasks & library

  • image text to text
  • transformers

Tags

  • transformers
  • granite4_vision
  • image-text-to-text
  • conversational
  • custom_code
  • en

Technical specifications

Parameters4B
Librarytransformers
Languagesen
Licenseapache-2.0