// RUN โ€” FITS

Can the Apple M1 Ultra 128GB run MegaMolBART?

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

MegaMolBART on the Apple M1 Ultra 128GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 1734k 6044.4-7288.9 t/s ~75.6-91.1 (slow)
Q8 yes 1734k 12088.9-14577.8 t/s ~151.1-182.2 (slow)
Q4 yes 1735k 21587.3-26031.7 t/s ~269.8-325.4 (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 MegaMolBART?โ–ถ

Yes. At Q4 it generates ~21587.3-26031.7 tok/s and fits up to 1735k context; beyond that it spills to SSD swap and slows to ~269.8-325.4 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1735k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.