RELEASE · MODELS · #2673
Liquid announces LFM3 family of 2B-class multimodal foundation models including LFM3-1.7B-Base
Liquid introduces LFM3, a new generation of Liquid Foundation Models that bring text, vision (including video), audio, omni and decision variants onto a shared 2B-class backbone (branched from LFM3-1.7B-Base). Key changes include a tri-hybrid architecture and training recipe that improve capability-per-parameter, a 256K context window for the text model, new lightweight vision and audio encoders (and LiquidCodec for audio), and designs aimed at single-GPU fine-tuning and on-device deployment.
KEY POINTS
- Liquid introduces LFM3, a new generation of Liquid Foundation Models that bring text, vision (including video), audio, omni and decision variants onto a shared 2B-class backbone (branched from LFM3-1.7B-Base).
- Key changes include a tri-hybrid architecture and training recipe that improve capability-per-parameter, a 256K context window for the text model, new lightweight vision and audio encoders (and LiquidCodec for audio), and designs aimed at single-GPU fine-tuning and on-device deployment.
- This matters because LFM3 targets on-device and agentic use cases with higher capability-per-parameter, long-context support, and single-GPU fine-tuning, lowering the resources needed to build domain-specialized multimodal agents.
WHY IT MATTERS
This matters because LFM3 targets on-device and agentic use cases with higher capability-per-parameter, long-context support, and single-GPU fine-tuning, lowering the resources needed to build domain-specialized multimodal agents.