Key Info

Liquid AI announced LFM3, its new generation of Liquid Foundation Models, featuring a tri-hybrid architecture and new multimodal encoders. The family includes six model instances spanning text, audio, vision and omni modalities, for both generative and decision-making tasks.

Highlights

  • Six model instances across text, audio, vision and omni modalities
  • New tri-hybrid architecture and new multimodal encoders
  • Positioned as a model suite for specialized intelligence on edge devices
  • LFM3-1.7B highlighted as a strong agentic model