// RUN โ€” FITS

Can the Apple M2 Ultra 192GB run UDSMProt?

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

UDSMProt on the Apple M2 Ultra 192GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 2613k 9610-11588.5 t/s ~120.1-144.9 (slow)
Q8 yes 2613k 19220-23177.1 t/s ~240.3-289.7 (slow)
Q4 yes 2614k 34321.5-41387.7 t/s ~429-517.3 (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 UDSMProt?โ–ถ

Yes. At Q4 it generates ~34321.5-41387.7 tok/s and fits up to 2614k context; beyond that it spills to SSD swap and slows to ~429-517.3 tok/s.

How much context fits?โ–ถ

At Q4, up to about 2614k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.