// RUN โ€” FITS

Can the Apple M2 Ultra 64GB run ADM?

Yes โ€” here's how fast and up to what context, with real measured numbers.

ADM on the Apple M2 Ultra 64GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 839k 486.6-586.8 t/s ~6.1-7.3 (slow)
Q8 yes 847k 973.2-1173.5 t/s ~12.2-14.7 (slow)
Q4 yes 851k 1737.8-2095.6 t/s ~21.7-26.2 (slow)

Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.

FAQ

Can the Apple M2 Ultra 64GB run ADM?โ–ถ

Yes. At Q4 it generates ~1737.8-2095.6 tok/s and fits up to 851k context; beyond that it spills to SSD swap and slows to ~21.7-26.2 tok/s.

How much context fits?โ–ถ

At Q4, up to about 851k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.