hugpadhugpad

LiquidAI / LFM3-VL-2B

Vision1.9B9.1K201Updated Oct 28, 2026
Hugging Face

Downloads

9.1K

Likes

201

Last updated

Oct 28, 2026

License

lfm1.0

LFM3-VL-2B is a vision-language model for on-device visual understanding. It takes text, images, and video as input, and combines the LFM3 language model with a new in-house vision encoder.

Tasks & library

  • image text to text
  • transformers

Tags

  • transformers
  • lfm3_vl
  • image-text-to-text
  • liquid
  • lfm3
  • edge

Technical specifications

Parameters1.9B
Librarytransformers
Languages16 languages
Base modelLiquidAI/LFM3-1.7B-Base
Licenselfm1.0