// RUN — FITS

Can the Apple M2 Max 32GB run PIXART-α?

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

PIXART-α on the Apple M2 Max 32GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 398k 226.7-273.3 t/s ~5.7-6.8 (slow)
Q8 yes 407k 453.3-546.7 t/s ~11.3-13.7 (slow)
Q4 yes 411k 809.5-976.2 t/s ~20.2-24.4 (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 32GB run PIXART-α?

Yes. At Q4 it generates ~809.5-976.2 tok/s and fits up to 411k context; beyond that it spills to SSD swap and slows to ~20.2-24.4 tok/s.

How much context fits?

At Q4, up to about 411k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.