antirez runs local LLM tests on Mac Studio M3 Ultra with 512GB RAM

antirez · x · 2026-09-12

Redis creator antirez reports that running models locally on a Mac Studio M3 Ultra with 256GB of RAM "works well, as expected," and that his full residency tests were done on a 512GB unit provided via SSH by friends — further evidence that big-memory Apple Silicon is a practical local LLM inference platform.

Original post →

More from Infra

Infra channel →