Liquid AI Releases LFM3 Family of Foundation Models

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, plus decision models.

Highlights

• LFM3-1.7B: text model with a 256k context window
• LFM3-VL-2B: vision-language model supporting video input for spatial understanding
• LFM3-Audio-2B: supports tool calls, voice chat, and reasoning in 18 languages
• LFM3-Omni-2B: combines vision, audio, and language
• d1-2B and d1-Omni-2B: decision models with typed outputs