// RUN โ€” FITS

Can the Apple M4 Max 36GB run TiTok-L?

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

TiTok-L on the Apple M4 Max 36GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 462k 604.7-729.2 t/s ~11.1-13.4 (slow)
Q8 yes 467k 1209.4-1458.4 t/s ~22.1-26.7 (slow)
Q4 yes 469k 2159.6-2604.2 t/s ~39.6-47.7 (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 TiTok-L?โ–ถ

Yes. At Q4 it generates ~2159.6-2604.2 tok/s and fits up to 469k context; beyond that it spills to SSD swap and slows to ~39.6-47.7 tok/s.

How much context fits?โ–ถ

At Q4, up to about 469k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.