Cactus runs local speech-to-actions on a $10 ESP32 with sub-30MB models
alexcovo_eth · x · 2026-10-21
Cactus Compute demoed local speech-to-actions on a $10 ESP32. Its stack includes Whistle (16.9MB open speech model, 7 languages, CPU-only) and Needle 3 (an 8–29MB function-calling model claiming to beat models 10x its size), plus sub-2-bit quantization, hybrid cloud fallback, and a Pebble partnership.
More from Embodied
- SF hard-tech crowd hosts real humanoid robot fight night — edgarpavlovsky · 2026-10-21
- REK robot fighting league footage goes viral: Terminator-style mechs battle in the cage — edgarpavlovsky · 2026-10-21
- Hot take: home automation wins by standardizing spaces, not building robots — alysha_lobo · 2026-10-21
- Photo: robot fighter carried off on a stretcher at SF bot-fighting event — itsclivetime · 2026-10-21
- CFG lifts single-step discrete action success from 27.1% to 49.2% in robot policy training — YouJiacheng · 2026-10-21
- Menlo Research open-sources Cyclotron, an RL training framework for its Asimov humanoid robot — freelerobot · 2026-10-21