allenai / Molmo2-8B

Vision8.7B41K198Updated Jan 23, 2026

Downloads

41K

Likes

198

Last updated

Jan 23, 2026

License

apache-2.0

Molmo2 is a family of open vision-language models developed by the Allen Institute for AI (Ai2) that support image, video and multi-image understanding and grounding. Molmo2 models are trained on publicly available third party datasets as referenced in our technical report and…

Tasks & library

  • image text to text
  • transformers

Tags

  • transformers
  • molmo2
  • image-text-to-text
  • multimodal
  • olmo
  • molmo

Technical specifications

Parameters8.7B
Librarytransformers
Languagesen
Base modelQwen/Qwen3-8B
Licenseapache-2.0