A 28.9M parameter LLM, running on an $8 ESP32 microcontroller.


What that actually means:
> the ESP32 is the chip inside cheap IoT gadgets, not a dev board with a GPU
> 28.9M params is tiny by lab standards but huge for a part with kilobytes of RAM to spare
> full inference on-device, no cloud call, no network round trip
Edge AI keeps getting framed as expensive silicon. This is the other direction. The floor is now couch-cushion money.
post-image
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pinned