jina-vlm
jina-vlm is a token-efficient 2.4B parameter vision-language model that achieves state-of-the-art multilingual VQA performance among open 2B-scale VLMs.
text + image → text · made by Jina AI
Sold by
Nobody in the catalogue publishes a price for this yet.
About
jina-vlm — a text model from Jina AI.
It takes text and images and returns text. It was published in November 2025. The catalogue files it under chat. Its weights are published, but the licence forbids selling what it produces.
Every current figure
- Maker
- Jina AI
- Register
- model
- Takes
- text + image
- Returns
- text
- Published
- November 2025
- Parameters
- 2.5 billion · read from its own weights
- Licence
- cc-by-nc-4.0
Known as 1 name
jinaai/jina-vlm