The Apple M5 Pro (24GB) carries 24GB of unified memory, about 16GB of which reaches a model under macOS, with 200 GB/s of memory bandwidth, making it a strong mid-range option for running local AI models. 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 a budget buys. Or the full specifications.
The Apple M5 Pro (24GB) has 24GB of unified memory, of which about 16GB reaches a model under macOS, and 200 GB/s memory bandwidth, making it a strong mid-range option for running local AI models. This guide covers which LLMs fit, expected tok/s performance, and recommended settings.
See the full Apple M5 Pro (24GB) specs page for detailed specifications, all compatible models, and speed estimates.