// RUN โ€” FITS

Can the Apple M3 Max 36GB run EMDR?

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

EMDR on the Apple M3 Max 36GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 458k 231.8-279.5 t/s ~7.7-9.3 (slow)
Q8 yes 465k 463.6-559.1 t/s ~15.5-18.6 (slow)
Q4 yes 468k 827.9-998.4 t/s ~27.6-33.3 (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 36GB run EMDR?โ–ถ

Yes. At Q4 it generates ~827.9-998.4 tok/s and fits up to 468k context; beyond that it spills to SSD swap and slows to ~27.6-33.3 tok/s.

How much context fits?โ–ถ

At Q4, up to about 468k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.