lfm3-vl

50 2 hours ago

LFM3-VL-2B is a vision-language model for on-device visual understanding.

vision tools thinking 2b

5 models

lfm3-vl:latest
280791ff33bb • 1.7GB • 125K context window •
Text, Image input • 2 hours ago
lfm3-vl:2b latest
280791ff33bb • 1.7GB • 125K context window •
Text, Image input • 2 hours ago
lfm3-vl:2b-mlx-bf16 MLX
2f90d817ad16 • 3.9GB • 125K context window •
Text, Image input • 2 hours ago
lfm3-vl:2b-mxfp8 MLX
08ced5a01d25 • 2.4GB • 125K context window •
Text, Image input • 2 hours ago
lfm3-vl:2b-nvfp4 MLX
280791ff33bb • 1.7GB • 125K context window •
Text, Image input • 2 hours ago