Model Releases

Liquid AI releases LFM2 on-device foundation models in 0.35B, 0.7B, and 1.2B sizes

Original title:Introducing LFM2: The Fastest On-Device Foundation Models on the Market

AI summary

Liquid AI released LFM2, a new generation of foundation models designed for on-device deployment, with CPU decoding and prefill speeds up to 2x faster than Qwen3 and 3x better training efficiency than the previous generation.

Key Takeaways

  • Liquid AI released LFM2
  • a new generation of foundation models designed for on-device deployment
  • with CPU decoding and prefill speeds up to 2x faster than Qwen3 and 3x better training efficiency…

Quick Facts

Published
Updated
Source
Liquid AI 模型与工程博客(网页)
Category
Model Releases
AI score
66
Read the original Read the full article at the original source
Why it matters

官方发布端侧模型系列,给出与 Qwen3 等同尺寸模型的速度和基准对比数据,适合关注本地部署选型的读者参考。

Source & copyright

This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.

Original article · AIHOT entry

How to Cite

When citing this article, keep the title, date, and permalink, and credit Orange News as the source.

Orange News: Liquid AI releases LFM2 on-device foundation models in 0.35B, 0.7B, and 1.2B sizes. July 10, 2025. https://new.nat6.net/en/news/cmtyo2iix03ecrog0tw02mei6/

View all →