← All companies

Lamb Labs

Active

World's fastest AI models

S26·Summer 2026·B2B·London, England, United Kingdom

About

Lamb Labs is building custom chips for AI inference and the world's fastest LLM model at the lowest power. We've developed a new post-training technique that converts existing models to a diffusion-based architecture that delivers 2× faster inference on existing GPUs. We then build the hardware, custom silicon chips targeting up to 20,000+ tok/s and a 63× higher intelligence per watt.

Change history · none recorded

No changes recorded yet. Subsequent syncs will populate this timeline as fields drift.