A new open-source inference engine called PicoLM claims to run a one-billion-parameter language model entirely locally, using roughly 45MB of RAM, no external dependencies, and hardware costing as little as $10. The project, developed by RightNow-AI and published on GitHub, targets a class of ultra-constrained devices that have largely been shut out of the on-device AI wave.
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.