15M/42M-param Llama split across two ESP32-S3s over 3 wires — too big for either chip alone. INT4, flash mmap, bit-exact verified.
-
Updated
Aug 15, 2026 - C
#
embedded-distributed-inference
Here is 1 public repository matching this topic...
Improve this page
Add a description, image, and links to the embedded-distributed-inference topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the embedded-distributed-inference topic, visit your repo's landing page and select "manage topics."