Software Engineer Runs Generative AI on 20-Year-Old PowerBook G4
In a blog post this week, software engineer Andrew Rossignol (my brother!) detailed how he managed to run generative AI on an old PowerBook G4.
While hardware requirements for large language models (LLMs) are typically high, this particular PowerBook G4 model from 2005 is equipped with a mere 1.5GHz PowerPC G4 processor and 1GB of RAM. Despite this 20-year-old hardware, my brother was able to achieve inference with Meta's LLM model Llama 2 on the laptop.
The experiment involved porting the open-source llama2.c project, and then accelerating performance with a PowerPC vector extension called AltiVec.
His full blog post offers more technical details about the project.
Similar examples of generative AI models running on the PlayStation 3, Xbox 360, and other old devices have surfaced in the news from time to time.
Popular Stories
Apple today released a new Pride Edition Sport Loop for the Apple Watch. The band features a rainbow design with 11 colors of woven nylon yarns.
The new Pride Edition Sport Loop is available to order now on Apple.com and in the Apple Store app in 40mm, 42mm, and 46mm sizes, and it will be available at Apple Store locations starting later this week. In the U.S., the band costs $49.
There...
iOS 26.5 includes three new features for iPhones, according to Apple's release notes for the update, which is expected to be released next week.
As discovered during beta testing, iOS 26.5 enables end-to-end encryption for RCS messaging between iOS and Android devices. Apple says this security upgrade is limited to supported carriers around the world and will continue to roll out....
Instagram will remove end-to-end encryption for direct messages between users from May 8, 2026. When the date comes around, Meta will potentially be able to see the contents of all messages between users on the social media platform.
Encrypting messages has been an optional feature in Instagram since 2023, but in March of this year the social media platform quietly updated a help page to say ...
