// RUN โ€” FITS

Can the Apple M4 Max 36GB run CRYSTALCODER?

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

CRYSTALCODER on the Apple M4 Max 36GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 134k 27.7-33.4 t/s ~0.5-0.6 (slow)
Q8 yes 185k 55.4-66.8 t/s ~1-1.2 (slow)
Q4 yes 207k 99-119.3 t/s ~1.8-2.2 (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 M4 Max 36GB run CRYSTALCODER?โ–ถ

Yes. At Q4 it generates ~99-119.3 tok/s and fits up to 207k context; beyond that it spills to SSD swap and slows to ~1.8-2.2 tok/s.

How much context fits?โ–ถ

At Q4, up to about 207k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.