apple silicon.

When does a GPU pay for itself in self-hosted AI inference, and when is a modern CPU the better answer? A reasoned comparison of four kinds of host (Raspberry Pi 5, Intel NUC 13, Mac Mini M4, a single-GPU box): what each can run, what it costs to keep on, and where the CPU wins. Orders of magnitude, not a measured benchmark.

Mac mini M4 and M4 Pro for local LLMs: 16 to 64 GB of unified memory at 120 or 273 GB/s, the two specs that decide which models load and how fast.

Fanless laptop with up to 24 GB unified memory. Runs Mistral 7B Q4 silently on the train. €1,299+.