femtoAI develops ultra-efficient AI inference technology designed to run directly on everyday devices without cloud connectivity. Founded in 2018 and emerging from Stanford University's Brains in Silicon Lab, the Silicon Valley-based company has raised $20.6M to pursue artificial intelligence at the extreme edge.
The company's technical work spans AI inference, neuromorphic computing, sparse processing, and edge AI. Its flagship product, the Sparse Processing Unit (SPU-001), is custom sparse processing hardware that achieves 100x energy efficiency and 10x model capacity compared to traditional AI processors. femtoAI also offers a full-stack solution combining ready-to-deploy AI models, a Software Development Kit (SDK), and custom hardware to deliver real-time AI on compact silicon.
These capabilities target applications across consumer electronics, smart home devices, wearables, robotics, autonomous vehicles, and healthcare. The technology is already shipping in real-world products, including the NewSound AI hearing aid, which demonstrates 100x power reduction and a 10x reduction in memory footprint. The company has also joined the NVIDIA Inception Program.
