lfm3-omni

85 2 hours ago

a single end-to-end model that understands text, images, video and audio, and answers in text and speech

vision tools audio 2b

5 models

lfm3-omni:latest
8c2f5a2d126d • 2.4GB • 125K context window •
Text, Image input • 2 hours ago
lfm3-omni:2b latest
8c2f5a2d126d • 2.4GB • 125K context window •
Text, Image input • 2 hours ago
lfm3-omni:2b-mlx-bf16 MLX
a3eb4ae57b32 • 4.5GB • 125K context window •
Text, Image input • 2 hours ago
lfm3-omni:2b-mxfp8 MLX
6836661470a1 • 3.1GB • 125K context window •
Text, Image input • 2 hours ago
lfm3-omni:2b-nvfp4 MLX
8c2f5a2d126d • 2.4GB • 125K context window •
Text, Image input • 2 hours ago