// RUN โ€” FITS

Can the Apple M1 Max 32GB run MegaMolBART?

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

MegaMolBART on the Apple M1 Max 32GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 415k 3022.2-3644.4 t/s ~75.6-91.1 (slow)
Q8 yes 416k 6044.4-7288.9 t/s ~151.1-182.2 (slow)
Q4 yes 416k 10793.7-13015.9 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 Max 32GB run MegaMolBART?โ–ถ

Yes. At Q4 it generates ~10793.7-13015.9 tok/s and fits up to 416k 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 416k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.