LiquidAI/LFM2-VL-3B
Image-Text-to-Text • 3B • Updated • 11.9k • 132
👁️ LFM2-VL
LFM2-VL is our first series of vision-language models, designed for on-device deployment.
-
-
LiquidAI/LFM2-VL-1.6B
Image-Text-to-Text • 2B • Updated • 5.09k • 226 -
LiquidAI/LFM2-VL-450M
Image-Text-to-Text • 0.5B • Updated • 15.5k • 146
LiquidAI/LFM2-VL-3B-GGUF
Image-Text-to-Text • 3B • Updated • 79.4k • 34Note GGUF checkpoints compatible with llama.cpp
-
LiquidAI/LFM2-VL-1.6B-GGUF
Image-Text-to-Text • 1B • Updated • 2.44k • 57 -
LiquidAI/LFM2-VL-450M-GGUF
Image-Text-to-Text • 0.4B • Updated • 90.9k • 40
mlx-community/LFM2-VL-3B-8bit
Image-Text-to-Text • 1B • Updated • 20 • 4Note Checkpoints compatible with Apple MLX
-
mlx-community/LFM2-VL-1.6B-8bit
Image-Text-to-Text • 0.7B • Updated • 43 • 10 -
mlx-community/LFM2-VL-450M-8bit
Image-Text-to-Text • 0.2B • Updated • 792 • 11 -
LFM2 Technical Report
Paper • 2511.23404 • Published • 55