// RUN โ€” FITS

Can the Intel Arc Pro B70 run UDSMProt?

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

UDSMProt on the Intel Arc Pro B70

QuantFits?Max contextSpeedBeyond context
FP16 yes 425k 6229.6-7733.2 t/s ~409.8-508.8 (slow)
Q8 yes 426k 12459.1-15466.5 t/s ~819.7-1017.5 (slow)
Q4 yes 426k 22248.4-27618.7 t/s ~1463.7-1817 (slow)

Estimate (memory-bound). Beyond "max context" the KV cache spills to system RAM offload (depends on your system RAM) and speed drops to the "beyond" figure.

FAQ

Can the Intel Arc Pro B70 run UDSMProt?โ–ถ

Yes. At Q4 it generates ~22248.4-27618.7 tok/s and fits up to 426k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1463.7-1817 tok/s.

How much context fits?โ–ถ

At Q4, up to about 426k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.