MLX-VLM

Liquid AI LFM2.5-VL-DSpark Speeds Vision AI Decoding Up to 3.13x

Liquid AI's 280M-parameter LFM2.5-VL-DSpark accelerates LFM2.5-VL-3B decoding up to 3.13x on devices and 2.66x on H100 with exact output across three runtimes.