A developer known as slvDev has squeezed a 28.9-million-parameter language model onto Espressif's ESP32-S3, an approximately $8 microcontroller, running the model entirely on-chip with no server connection and generating text at roughly 9.5 tokens per second. The demonstration, released as open source with firmware and training code on GitHub, pushes the boundary of what tiny, low-cost silicon can do without touching the cloud.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.