Cactus Compute

A San Francisco startup from Y Combinator's summer 2025 batch. It builds tiny on-device AI models and the open-source Cactus inference engine for phones, wearables, robots and other low-power hardware. Its Needle, Whistle and Mirage models are released under Apache 2.0.

  • United States
  • Company
  • 3 models

Models by Cactus Compute

Model Released Parameters Context License Smallest variant needs
Mirage Cactus Compute 51M – Apache 2.0 (Permissive) 0.0354 GB Laptop or phone
Whistle Cactus Compute 55M – Apache 2.0 (Permissive) 0.253 GB Laptop or phone
Needle 3 Cactus Compute 121M 8K Apache 2.0 (Permissive) 0.0835 GB Laptop or phone