Molmo2-4B
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.
text + image → text · made by Allen Institute for AI (Ai2)
Sold by
Nobody in the catalogue publishes a price for this yet.
About
Molmo2-4B — a text model from Allen Institute for AI (Ai2).
It takes text and images and returns text. It was published in December 2025. The catalogue files it under search. Its weights are published under APACHE-2.0, so you may run it on your own machine, or buy it from whoever serves it cheapest.
Every current figure
- Maker
- Allen Institute for AI (Ai2)
- Register
- model
- Takes
- text + image
- Returns
- text
- Published
- December 2025
- Parameters
- 4 billion · read from its own name
- Licence
- apache-2.0
Known as 1 name
allenai/Molmo2-4B