Announcement
Press Release
Device-native foundation models.
Advanced intelligence for processors outside of data centers. Built for the latency, privacy, and hardware constraints of the physical world.
Deployments
Phones, laptops, cars, space, e-commerce, financial services, bio, defence
Runtimes
llama.cpp, MLX, ONNX, CoreML, SGLang, vLLM
& more
We build efficient, general-purpose AI at every scale.
Explore our modelsDevelopersLEAP SDK
Specialize. Deploy. In minutes.
Fine-tune a model, bake it to any runtime, and ship. Leap is the fastest path from notebook to production.
Open the SDK
EnterprisePartnerships
Maximum intelligence, minimal compute.
Production-grade deployments with Mercedes-Benz and more — all running on the edge.
Talk to sales
ResearchThe frontier
Where the frontier moves.
Liquid neural networks, state-space models, and new training recipes. Published in the open.
Read our research
Achieve peak performance by fine-tuning LFMs for your use case.
The power of model customization directly in your hands.
LFMs are designed for rapid customization to achieve peak performance for specified use cases at a footprint small enough to run locally on your chosen hardware. Our full-stack solution includes architecture, optimization, and deployment engines to accelerate the path from prototype to product.