Is d1-Omni-2B state of the art?Pending benchmarks.Announced Oct 27, 2026; no independent results yet.
Liquid AI's decision model that also listens, built on LFM3-Omni-2B. It answers named questions about text, pictures, video and audio clips, written or spoken, in a single forward pass, with typed answers and calibrated probabilities instead of generated text or speech. Open weights under the LFM Open License v1.0.
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
- Base model
- LFM3-Omni-2B
- Input
- A state (text or JSON), pictures, a video, audio clips, and named questions, written or spoken
- Output
- Typed answers with probabilities; no generated tokens, transcript or speech
- Context
- 128K tokens
- Speech languages
- The 16 text languages except Hindi, Thai, Vietnamese and Indonesian
- 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.
- 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)
What the lab claims
Self-reported. Shown for context; not used in any verdict.
Lab claim: 84.5% on ESC-50 sound recognition and 92.5% spoken-language identification across 43 languages on FLEURS; 5.8 ms per decision on an NVIDIA H100 (12.4 ms with a 10-second clip).
Sources
LABLiquid AI: Introducing LFM3liquid.ai/blog/lfm3 · Oct 27, 2026REPOLiquidAI/d1-Omni-2B on Hugging Facehuggingface.co/LiquidAI/d1-Omni-2BTracking continues until an independent board lists it.