# Is LFM3-Omni-2B SOTA?

Pending benchmarks. Announced Oct 27, 2026; no independent results yet.

As of Nov 3, 2026, LFM3-Omni-2B is pending benchmarks on isitsota: announced Oct 27, 2026, with no independent results on the boards we track 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.

Canonical: https://isitsota.com/m/lfm3-omni-2b
Last updated: 2026-10-27
Tracking since: 2026-10-27

## Announced facts

| Fact | Value |
| --- | --- |
| 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.

## What would let us call it

Verdicts use only independent boards we already track. Two consecutive snapshots are required before any crown.

- [x] Publicly announced with a source
- [x] 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)

## 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).

## Sources

- LAB: [Liquid AI: Introducing LFM3](https://www.liquid.ai/blog/lfm3) (2026-10-27)
- REPO: [LiquidAI/LFM3-Omni-2B on Hugging Face](https://huggingface.co/LiquidAI/LFM3-Omni-2B)

Tracking continues until an independent board lists it.

## Related

- Lab: [Liquid AI](https://isitsota.com/labs/liquid.md)
- All pending releases: https://isitsota.com/releases.md
- JSON: https://api.isitsota.com/v1/models/lfm3-omni-2b