// RUN โ€” FITS

Can the Apple M3 Max 48GB run KeTu (Kolors)?

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

KeTu (Kolors) on the Apple M3 Max 48GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 557k 52.3-63.1 t/s ~1.3-1.6 (slow)
Q8 yes 597k 104.6-126.2 t/s ~2.6-3.2 (slow)
Q4 yes 614k 186.8-225.3 t/s ~4.7-5.6 (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 48GB run KeTu (Kolors)?โ–ถ

Yes. At Q4 it generates ~186.8-225.3 tok/s and fits up to 614k context; beyond that it spills to SSD swap and slows to ~4.7-5.6 tok/s.

How much context fits?โ–ถ

At Q4, up to about 614k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.