AITechRadarabout 2 hours ago
Small LLM Runs on $10 Microcontroller
3 min read
A developer, slvDev, runs a 28.9-million-parameter language model on an ESP32-S3 microcontroller at 9.88 tokens per second, fully offline. The model fits in 512KB of RAM by using flash storage. The esp32-ai project is on GitHub under an MIT license.
Level
Hype check
Tap to vote and see what everyone thinks.
Summary by ByteBrief
