Liquid AI releases LFM2.5-VL-450M – structured visual understanding at 240ms
Today, we release LFM2.5-VL-450M our most capable vision-language model for edge deployment. It processes a 512×512 image in 240ms and it is fast enough to reason about every frame in a 4 FPS video stream. It builds on LFM2-VL-450M with three new…