lfm3-vl

18.4K 1 week ago

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

vision tools thinking 2b

9 models

lfm3-vl:latest
b663c9779257 • 1.5GB - 1.7GB • 125K context window •
Text, Image input • 1 week ago
lfm3-vl:2b latest
b663c9779257 • 1.5GB - 1.7GB • 125K context window •
Text, Image input • 1 week ago
lfm3-vl:2b-mlx-bf16 MLX
2f90d817ad16 • 3.9GB • 125K context window •
Text, Image input • 1 week ago
lfm3-vl:2b-mxfp8 MLX
08ced5a01d25 • 2.4GB • 125K context window •
Text, Image input • 1 week ago
lfm3-vl:2b-nvfp4 MLX
280791ff33bb • 1.7GB • 125K context window •
Text, Image input • 1 week ago
lfm3-vl:2b-qad-q4_0
eefca5a1a2dc • 1.4GB • 125K context window •
Text, Image input • 1 week ago
lfm3-vl:2b-q4_K_M
00ca45bf65a5 • 1.5GB • 125K context window •
Text, Image input • 1 week ago
lfm3-vl:2b-q8_0
e2be50ac28b2 • 2.2GB • 125K context window •
Text, Image input • 1 week ago
lfm3-vl:2b-bf16
dd69080d181a • 3.8GB • 125K context window •
Text, Image input • 1 week ago