Pending benchmarksTracking since Oct 27, 2026
Is LFM3-Omni-2B state of the art?Pending benchmarks.Announced Oct 27, 2026; no independent results yet.
Liquid AI's first omni model: one on-device model that takes text, images, video with its soundtrack, and audio, and answers in text and speech, in place of separate speech recognition, vision-language, language and text-to-speech models. Open weights under the LFM Open License v1.0.
Announced facts
The details so far
- Lab
- Liquid AI
- Announced
- Oct 27, 2026
- API
- Live · Liquid AI API and Playground, per Liquid's blog
- Open weights
- Published
- Parameters
- 2.17B
- Architecture
- LFM3 backbone, LFM3 vision encoder, LFM3 causal audio encoder and LiquidCodec audio tokenizer
- Inputs
- Text, images, video with or without its soundtrack (2 fps), and 16 kHz audio
- Outputs
- Text, 24 kHz speech, or interleaved text and speech
- Context
- 32K tokens (input + output)
- Reasoning
- Non-reasoning model (no thinking mode)
- License
- LFM Open License v1.0
Tags marked unsure are not stated on the lab's own pages.
Next steps
What would let us call it
Verdicts use only independent boards we already track. Two consecutive snapshots are required before any crown.
- Publicly announced with a source
- Usable by the public (API or weights)
- Listed on an independent board we track
- Enough results for a rank in a category
- Holds across two snapshots (crowns only)
Self-reported
What the lab claims
Self-reported. Shown for context; not used in any verdict.
Lab claim: 47.1 on WorldSense and 48.2 on OmniBench Speech, vs 45.4 and 48.0 for Qwen2.5-Omni-7B (10.7B).
Receipts
Sources
LABLiquid AI: Introducing LFM3liquid.ai/blog/lfm3 · Oct 27, 2026REPOLiquidAI/LFM3-Omni-2B on Hugging Facehuggingface.co/LiquidAI/LFM3-Omni-2BTracking continues until an independent board lists it.