# Liquid AI's LFM3-Omni-2B brings any-to-any AI to the edge

> The 2-billion-parameter model combines vision, audio and speech-to-speech in a package small enough to run on device.

Published by The Open Weights on Oct 21, 2026. Canonical: https://theopenweights.com/news/lfm3-omni-2b-aqpy

## Key facts

- Company: LiquidAI
- Model: LFM3-Omni-2B
- Version: Omni-2B
- Category: Any-to-Any
- Modalities: Any-to-Any, Text → Speech, Vision-Language
- License: Other (Open weights, commercial use allowed)
- Parameters: 2B
- Context window: 128K tokens
- Architecture: Lfm3OmniForConditionalGeneration
- Precision: BF16
- Weights size: 4.3 GB
- Significance: notable
- Published: 2026-10-21
- Last verified: 2026-10-30
- Hugging Face: https://huggingface.co/LiquidAI/LFM3-Omni-2B
- Canonical URL: https://theopenweights.com/news/lfm3-omni-2b-aqpy

Liquid AI has released [LFM3-Omni-2B](https://huggingface.co/LiquidAI/LFM3-Omni-2B), a compact multimodal model that aims to pack a wide range of input and output types into a footprint suited for edge hardware. At roughly 2 billion parameters, it is designed to run where cloud-scale models cannot.

The model is described as "any-to-any," meaning it can take in and produce across multiple modalities. According to the release, that includes vision and audio understanding alongside text, plus speech-to-speech capability — a notable combination for a model of this size.

## Why it matters

Most multimodal systems that handle both vision and real-time speech remain large and tethered to datacenter inference. A 2B model that spans these tasks fits Liquid AI's broader focus on efficient architectures intended for on-device use. Smaller any-to-any models open the door to:

- Local voice assistants that respond without a network round-trip
- Privacy-sensitive applications where audio and images stay on the device
- Lower-cost deployment on consumer and embedded hardware

The model is published under a custom license, so teams evaluating it for production should review the terms on the [model page](https://huggingface.co/LiquidAI/LFM3-Omni-2B) before building on it. As with any early release, real-world performance on vision, audio and speech tasks will be the measure of how far a model this compact can stretch.

## Get the model

- [Hugging Face](https://huggingface.co/LiquidAI/LFM3-Omni-2B)

## Sources

- [LiquidAI/LFM3-Omni-2B](https://huggingface.co/LiquidAI/LFM3-Omni-2B) — Hugging Face, Oct 21, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Liquid AI's LFM3-Omni-2B brings any-to-any AI to the edge", The Open Weights, Oct 21, 2026, https://theopenweights.com/news/lfm3-omni-2b-aqpy