// RUN โ€” FITS

Can the Apple M3 Max 128GB run ChemBERTa?

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

ChemBERTa on the Apple M3 Max 128GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 1731k 1088-1312 t/s ~27.2-32.8 (slow)
Q8 yes 1733k 2176-2624 t/s ~54.4-65.6 (slow)
Q4 yes 1734k 3885.7-4685.7 t/s ~97.1-117.1 (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 128GB run ChemBERTa?โ–ถ

Yes. At Q4 it generates ~3885.7-4685.7 tok/s and fits up to 1734k context; beyond that it spills to SSD swap and slows to ~97.1-117.1 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1734k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.