Google and Synaptics Preview Coral Microcontroller for On-Device AI at Under 6 Milliwatts
lmoroney · x · 2026-10-19
Google and Synaptics previewed a Coral-based microcontroller built for very low-power on-device AI, ahead of a formal launch on October 20.
- Pairs Google's Coral NPU with Synaptics' Torq NPU and Arm CPUs
- Google Research says the new Coral M2 vector processor runs on-device inference at an average draw under 6 milliwatts
- Ships with an open-source MLIR compiler compatible with standard ML frameworks; developers can already prototype on Coralboard
- Author suggests embedded ML educators sketch tiny vision or keyword-spotting demos that fit a few-milliwatt budget
Related event: Google and Synaptics Preview Ultra-Low-Power On-Device AI Microcontroller(2 posts)→
More from Infra
- Jev Router cuts coding agent costs 67-85% by routing tasks to cheap open models — HowDevelop · 2026-10-19
- Baidu's Virtual Head Attention cuts KV cache 4-7x with zero custom kernels — burny_tech · 2026-10-19
- Server memory spot growth slows to +0.6% as storage stocks fall 5-7% in a day — tengyanAI · 2026-10-19
- RTX Spark vs M5 Max: local Qwen 3.8 27B benchmark shows NVIDIA wins on compute — draginol · 2026-10-19
- Biscotti: a self-hosted Instinct-like iMessage assistant in ~850 LOC — lucasgelfond · 2026-10-19
- ComfyUI Portable slashes RAM usage vs Desktop in side-by-side video generation test — phalanx2357 · 2026-10-19