# Liquid AI releases LFM3, a family of six open-weight models for on-device tasks

> Original title: You don't see releases like this every day.

- Source: Elvis Saravia
- Published: 2026-10-27T17:33:43.000Z
- Bad Influence: https://badinfluence.news/items/mjnay0h9wrfsajnb0tsz8nnsh
- Original: https://x.com/omarsar0/status/2115134865733828918

## Summary

Liquid AI has released LFM3, a family of about 2B open-weight models covering text, vision, audio, omni, and decision tasks on one shared backbone. The author says LFM3-1.7B supports a 256K context and scores 38.4 on WebArena-Verified, versus 28.9 for Qwen3.5-9B in Liquid's own evaluation. The models can be fine-tuned on a single GPU.

## Post

You don't see releases like this every day. 

Liquid AI just released LFM3, a family of ~2B open-weight models for text, vision, audio, omni, and decision tasks, all on one shared backbone.

LFM3-1.7B is trained to run in agent harnesses like Hermes Agent and Pi, with a 256K context. 

On WebArena-Verified, it scores 38.4 vs. 28.9 for Qwen3.5-9B in Liquid's evaluation. Models can be fine-tuned on a single GPU.

This series of models has huge potential for always-on local agents.

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Famplify_video_thumb%2F2115132872449236992%2Fimg%2F8ecGqdkJRkMDdxkc.jpg&mode=thumb&exp=1793404800&sig=19417dfd8204a26e)

## Quoted post @liquidai

> Introducing 𝙻𝙵𝙼𝟹: our new generation of Liquid Foundation Models. With a new tri-hybrid architecture and new multimodal encoders, the LFM3 family is the ideal model suite for specialized intelligence.
> 
> > 6 model instances, across text, audio, vision, and omni modalities, generative and decision models.
> > 𝙻𝙵𝙼𝟹-𝟷.𝟽𝙱: text, 256k context window.
> > 𝙻𝙵𝙼𝟹-𝚅𝙻-𝟸𝙱: vision-language model with video-input support for spatial understanding
> > 𝙻𝙵𝙼𝟹-𝙰𝚞𝚍𝚒𝚘-𝟸𝙱: tool calls, voice chat, reasoning in 18 languages.
> > 𝙻𝙵𝙼𝟹-𝙾𝚖𝚗𝚒-𝟸𝙱: an omni model combines vision, audio, and language.
> > 𝚍𝟷-𝟸𝙱 and 𝚍𝟷-𝙾𝚖𝚗𝚒-𝟸𝙱: decision models with typed outputs and calibrated probabilities in a single pass. Omni adds audio input.
> > fine-tune on 1 GPU.
> > a new tri-hybrid architecture
> > architecture optimized for 14 processor classes across GPUs, CPUs, and NPUs.
> > 𝙻𝙵𝙼𝟹-𝚅𝙻-𝟸𝙱 is a beast. It performs competitively with Gemma 4 12B (6x larger), and Gemini 3.5 Flash Lite, and GPT-5.6 Luna, with 1.9B parameters.
> > 𝙻𝙵𝙼𝟹-𝟷.𝟽𝙱 is #1 on the Pareto frontier of device intelligence 𝚙𝚒𝚙𝚎𝚝𝚝𝚎.𝚕𝚒𝚚𝚞𝚒𝚍.𝚊𝚒
> 
> Every modality for specialized intelligence. Pick the one that fits your use case, customize it, and run it on-device.
> 
> 1/ 🧵

https://x.com/liquidai/status/2115128329003303107