// RUN โ€” FITS

Can the Apple M2 Max 64GB run phi-3.5-mini?

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

phi-3.5-mini on the Apple M2 Max 64GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 740k 35.8-43.2 t/s ~0.9-1.1 (slow)
Q8 yes 798k 71.6-86.3 t/s ~1.8-2.2 (slow)
Q4 yes 824k 127.8-154.1 t/s ~3.2-3.9 (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 Max 64GB run phi-3.5-mini?โ–ถ

Yes. At Q4 it generates ~127.8-154.1 tok/s and fits up to 824k context; beyond that it spills to SSD swap and slows to ~3.2-3.9 tok/s.

How much context fits?โ–ถ

At Q4, up to about 824k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.