// RUN โ€” FITS

Can the Apple M3 Max 48GB run Distilled Grandmaster?

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

Distilled Grandmaster on the Apple M3 Max 48GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 628k 503.7-607.4 t/s ~12.6-15.2 (slow)
Q8 yes 632k 1007.4-1214.8 t/s ~25.2-30.4 (slow)
Q4 yes 634k 1798.9-2169.3 t/s ~45-54.2 (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 Distilled Grandmaster?โ–ถ

Yes. At Q4 it generates ~1798.9-2169.3 tok/s and fits up to 634k context; beyond that it spills to SSD swap and slows to ~45-54.2 tok/s.

How much context fits?โ–ถ

At Q4, up to about 634k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.