Device-native foundation models.

Advanced intelligence for processors outside of data centers. Built for the latency, privacy, and hardware constraints of the physical world.

• Advanced intelligence for processors outside of data centers. Built for the latency, privacy, and hardware constraints of the physical world.
• 56 Models shipped, 42.6M downloads, 3400+ variants.
• Deploy on phones, laptops, cars, space, e-commerce, financial services, bio, and defense.
• Runs on vLLM, SGLang, llama.cpp, TensorRT-LLM, Core ML, MLX, MNN, and ONNX.