Skip to main content

Welcome to LFM Docs! 👋

LFM2 is a new generation of hybrid models developed by Liquid AI, specifically designed for edge AI and on-device deployment.

Why LFM2?

Built on a new hybrid architecture, LFM2 sets a new standard in terms of quality, speed, and memory efficiency.

  ⚡ 3x faster training - New hybrid architecture accelerates training and inference

  🏆 State-of-the-art quality - Outperforms similar-sized models on benchmarks

  💾 Memory efficient - Optimized for resource-constrained environments

  🌐 Deploy anywhere - Compatible with major inference frameworks and platforms

Learn more about the architecture →

See also

📚 Liquid AI Cookbook - Explore examples, tutorials, and end-to-end applications built with LFM2 models and the LEAP SDK. Find fine-tuning notebooks, edge deployment examples, and community-built apps to get started quickly.

Model Families

Explore all models →

Get Started