// RUN โ€” FITS

Can the Intel Arc Pro B70 run DistilProtBert?

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

DistilProtBert on the Intel Arc Pro B70

QuantFits?Max contextSpeedBeyond context
FP16 yes 419k 766.6-951.7 t/s ~50.4-62.6 (slow)
Q8 yes 423k 1533.2-1903.3 t/s ~100.9-125.2 (slow)
Q4 yes 424k 2737.9-3398.8 t/s ~180.1-223.6 (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 DistilProtBert?โ–ถ

Yes. At Q4 it generates ~2737.9-3398.8 tok/s and fits up to 424k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~180.1-223.6 tok/s.

How much context fits?โ–ถ

At Q4, up to about 424k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.