// RUN โ€” FITS

Can the Apple M1 Ultra 128GB run Distilled Grandmaster?

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

Distilled Grandmaster on the Apple M1 Ultra 128GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 1727k 1007.4-1214.8 t/s ~12.6-15.2 (slow)
Q8 yes 1731k 2014.8-2429.6 t/s ~25.2-30.4 (slow)
Q4 yes 1733k 3597.9-4338.6 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 M1 Ultra 128GB run Distilled Grandmaster?โ–ถ

Yes. At Q4 it generates ~3597.9-4338.6 tok/s and fits up to 1733k 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 1733k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.