LiquidAI/LFM2-VL-3B
Image-Text-to-Text • 3B • Updated
• 6.93k • 131
👁️ 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 • 2.62k • 221 -
LiquidAI/LFM2-VL-450M
Image-Text-to-Text • 0.5B • Updated • 15k • 144
LiquidAI/LFM2-VL-3B-GGUF
Image-Text-to-Text • 3B • Updated • 57.4k • 33Note GGUF checkpoints compatible with llama.cpp
-
LiquidAI/LFM2-VL-1.6B-GGUF
Image-Text-to-Text • 1B • Updated • 4.23k • 56 -
LiquidAI/LFM2-VL-450M-GGUF
Image-Text-to-Text • 0.4B • Updated • 55k • 36
mlx-community/LFM2-VL-3B-8bit
Image-Text-to-Text • 1B • Updated • 32 • 3Note Checkpoints compatible with Apple MLX
-
mlx-community/LFM2-VL-1.6B-8bit
Image-Text-to-Text • 0.7B • Updated • 38 • 9 -
mlx-community/LFM2-VL-450M-8bit
Image-Text-to-Text • 0.2B • Updated • 586 • 10 -
LFM2 Technical Report
Paper • 2511.23404 • Published • 53