Models built forreal-world constraints.

Frontier-grade intelligence at a fraction of the compute, on any hardware, on or off the cloud.

Explore LFMs

Vision-Language Models

Multimodal models using vision and text inputs and outputs with capabilities designed for low latency and device aware deployment.

Audio Models

End-to-end foundation models for audio and text generation, designed for low-latency, responsive, high-quality conversations.

  • LFM2.5-Audio-1.5B-JP

Omni Models

End-to-end multimodal models that take text, image, and audio in one model and respond in kind, without stitching separate pipelines together.

Nano Models

Tiny customized models for specific tasks and knowledge.

Every LFM is free to download, run, and fine-tune — including commercially — until your company passes $10M in annual revenue. See pricing & licensing

Pipette

On-device performance for

Explore more quants, runtimes, modalities, and metrics on Pipette.

Deploy anywhere