Open-weight multimodal model family
LFM3
LFM3 is the third generation of Liquid AI's Liquid Foundation Models, announced on 27 October 2026. The first release has six open-weight models of about 2B parameters for text, vision, audio, omni and decision tasks, all built on the LFM3-1.7B-Base backbone and designed to run and be fine-tuned on edge devices.
Last reviewed 28 Oct 2026 · by Liquid AI
Facts at a glance
| Developer | Liquid AI |
|---|---|
| Released | 27 October 2026 source |
| Models in first release | Six models of about 2B parameters: text, vision, audio, omni and two decision models source |
| Pre-training data | 22T tokens source |
| Context window (text model) | 256K tokens source |
| Architecture | 24 layers: 13 gated short convolutions, 5 sliding-window attention, 6 global attention source |
| License | LFM Open License v1.0 |
Questions people ask
- When was LFM3 released?
- Liquid AI announced LFM3 and published the open weights on 27 October 2026.
- How big are the LFM3 models?
- The first release covers models of about 2B parameters. The text model, LFM3-1.7B, has 1.7B parameters and fits in about 1 GB at 4-bit precision, according to Liquid AI.