# Liquid AI launches LFM3 open-weight models, with a 1.7B text model beating its 2.6B predecessor

> Original title: Liquid AI just launched LFM3, an open-weight model family whose 1.7B text model beats its 2.6B predecessor.

- Source: Rohan Paul
- Published: 2026-10-27T17:51:06.000Z
- Bad Influence: https://badinfluence.news/items/tjomv8msd4sgy2ysvq17idd6m
- Original: https://x.com/rohanpaul_ai/status/2115139239772135897

## Summary

Liquid AI has launched LFM3, an open-weight model family, and the author says its 1.7B text model beats the 2.6B LFM2.5 predecessor. The gain is attributed to a tri-hybrid design of 24 layers, with 13 short convolutions, 5 sliding-window attention layers and 6 global attention layers. On AutomationBench, Liquid reports 41.29 for the 1.7B model against 15.10 for Qwen3.5-9B.

## Post

Liquid AI just launched LFM3, an open-weight model family whose 1.7B text model beats its 2.6B predecessor.

The gain comes from a tri-hybrid design: of 24 layers, 13 are short convolutions, 5 use 256-token sliding-window attention and 6 attend globally.

That efficiency carries into agent benchmarks run by Liquid, where the 1.7B model scores 41.29 on AutomationBench while Qwen3.5-9B manages 15.10.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHVp6ZhKbUAA7d9e.jpg&mode=thumb&exp=1793404800&sig=27add42c7fd50566)

## 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