Mac Studio for local AI

Every Mac Studio generation, with the memory bandwidth and unified memory that decide which models it can run. Pick a chip for its full model fit breakdown.

The M3 Ultra is the current generation at 819 GB/s and up to 512 GB. On the used market the M2 Ultra is the one to look for: 800 GB/s and up to 192 GB, which is the pairing that decides what runs, and neither figure changes with the age of the machine.

Comparing against a model instead?

Start from the model and see every Mac that runs it, with fit ratings and speed estimates.

Browse the model database