// RUN โ€” FITS

Can the Apple M4 Max 36GB run ZymCTRL?

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

ZymCTRL on the Apple M4 Max 36GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 449k 251.5-303.3 t/s ~4.6-5.6 (slow)
Q8 yes 460k 503.1-606.7 t/s ~9.2-11.1 (slow)
Q4 yes 465k 898.4-1083.3 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 M4 Max 36GB run ZymCTRL?โ–ถ

Yes. At Q4 it generates ~898.4-1083.3 tok/s and fits up to 465k 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 465k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.