Bonsai: A 27B reasoning model on a 16 GB M2 Mac, with Ferrox

Posted by antonellof on Saturday September 19, 2026 @03:52AM
from the medium.com dept.

( 1 comment | 3 points | on HN )

Re:Bonsai: A 27B reasoning model on a 16 GB M2 Mac, with Ferrox by antonellof on Saturday September 19, 2026 @03:52AM (#49764354)

Run a 27B reasoning model locally on a 16GB M2 Mac. Ferrox + ternary quantization delivers 5.9GB models without sacrificing much quality.

[ Parent | on HN ]