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
While the 14-inch and 16-inch MacBook Pro were just updated with M5 Pro and M5 Max chips last month, bigger changes are reportedly around the corner.
According to Bloomberg's Mark Gurman, the higher-end MacBook Pro models will be receiving a major redesign by early 2027, and he said that Apple might use "MacBook Ultra" branding for them. If so, the MacBook Ultra would likely be a...
A recent leak provides our best look yet at the design of Apple's upcoming iPhone 18 Pro and iPhone 18 Pro Max models.
Leaker Sonny Dickson recently shared images of the first iPhone 18 Pro, iPhone 18 Pro Max, and foldable iPhone dummy models. The images largely conform with rumors about the designs of the three devices and provide the first real visual confirmation of how they will look.
...
Apple today announced the launch of a new subscription option for App Store developers: monthly subscriptions with a 12-month commitment. The new option allows developers to offer subscribers discounted pricing typically associated with an annual subscription but paid on a monthly basis to keep payments more affordable.
This new payment option allows you to offer subscribers more affordable...