The Apple M1 Ultra (128GB) carries 128GB of unified memory, about 96GB of which reaches a model under macOS, with 800 GB/s of memory bandwidth, making it one of the strongest machines you can run a local model on. Here is which models fit, how fast they run, and what quantisation gives the best balance of quality and speed.
Already have it? Find the best model for it. Still choosing? See what else $4,999 buys. Or the full specifications.
The Apple M1 Ultra (128GB) has 128GB of unified memory, of which about 96GB reaches a model under macOS, and 800 GB/s memory bandwidth, making it one of the strongest machines you can run a local model on. This guide covers which LLMs fit, expected tok/s performance, and recommended settings.
See the full Apple M1 Ultra (128GB) specs page for detailed specifications, all compatible models, and speed estimates. Current price: $4999.