Lightning fast chips with hardcoded AI models
Lamb Labs is building MPUs (Model Processing Units), custom chips that hardcode LLM weights directly into the chip. Unlike GPUs, which move weights between memory and compute, MPUs keep the model on-chip, targeting up to 20,000+ tok/s and a 63× higher intelligence per watt. Lamb Labs is a Y Combinator company (Summer 2026). YC-listed status: Active.