MacBook Air for local AI

Every MacBook Air 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 M5 is the current generation at 153 GB/s and up to 32 GB. On the used market the M4 is the one to look for: 120 GB/s and up to 32 GB, which is the pairing that decides what runs, and neither figure changes with the age of the machine.

What comes next

Projection dated 2026-09-08

Apple has not announced any of this. The M7 Max and Ultra are the first parts Apple designed after cancelling a generation to reach them, so extrapolating from the M5 under-represents them. These rows assume LPDDR6, whose wider channels grow every bus by half, at its top speed bin by the time the Max and Ultra ship. The 1.5 TB Ultra ceiling is Bloomberg's reported design target, and whether that configuration ships depends on the memory market. Stacked memory or a new package fabric would land above these numbers; nobody outside Apple can price that yet.

M6Projected

Shipping chip, not yet in this Mac · expected 2026

153 to 170 GB/s · 16 to 32 GB unified memory

12-core CPU · 12-core GPU · 76 TOPS Neural Engine

Would hold about a 42B model at Q4

M7Projected

Projected chip · expected 2027

240 GB/s · 16 to 48 GB unified memory

12-core CPU · 12 or 16-core GPU · 76 TOPS Neural Engine

Would hold about a 63B model at Q4

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