// RUN โ€” FITS

Can the Apple M3 Max 128GB run MSA Transformer?

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

MSA Transformer on the Apple M3 Max 128GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 1732k 1360-1640 t/s ~34-41 (slow)
Q8 yes 1733k 2720-3280 t/s ~68-82 (slow)
Q4 yes 1734k 4857.1-5857.1 t/s ~121.4-146.4 (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 M3 Max 128GB run MSA Transformer?โ–ถ

Yes. At Q4 it generates ~4857.1-5857.1 tok/s and fits up to 1734k context; beyond that it spills to SSD swap and slows to ~121.4-146.4 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.