// RUN โ€” FITS

Can the Apple M3 Max 64GB run ZymCTRL?

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

ZymCTRL on the Apple M3 Max 64GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 833k 184.3-222.2 t/s ~4.6-5.6 (slow)
Q8 yes 845k 368.6-444.4 t/s ~9.2-11.1 (slow)
Q4 yes 850k 658.1-793.7 t/s ~16.5-19.8 (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 M3 Max 64GB run ZymCTRL?โ–ถ

Yes. At Q4 it generates ~658.1-793.7 tok/s and fits up to 850k context; beyond that it spills to SSD swap and slows to ~16.5-19.8 tok/s.

How much context fits?โ–ถ

At Q4, up to about 850k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.