// RUN โ€” FITS

Can the Apple M2 Ultra 192GB run MSA Transformer?

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

MSA Transformer on the Apple M2 Ultra 192GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 2611k 2720-3280 t/s ~34-41 (slow)
Q8 yes 2612k 5440-6560 t/s ~68-82 (slow)
Q4 yes 2613k 9714.3-11714.3 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 M2 Ultra 192GB run MSA Transformer?โ–ถ

Yes. At Q4 it generates ~9714.3-11714.3 tok/s and fits up to 2613k 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 2613k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.