AIMarkTechPostabout 2 hours ago
Liquid AI Releases LFM3 Multimodal Models
4 min read
Liquid AI releases LFM3, a family of six open-weight 2B-class multimodal models sharing one shared backbone. The suite covers text, vision, audio, omni and decision tasks, with LFM3-1.7B averaging 49.37 across 29 benchmarks. It fits in about 1 GB of memory at 4-bit and beats Qwen3.5-9B on specific agent results like BFCL V4.
Level
Hype check
Tap to vote and see what everyone thinks.