// RUN โ€” FITS

Can the Intel Arc Pro B50 run DistilProtBert?

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

DistilProtBert on the Intel Arc Pro B50

QuantFits?Max contextSpeedBeyond context
FP16 yes 195k 282.4-350.6 t/s ~50.4-62.6 (slow)
Q8 yes 198k 564.9-701.2 t/s ~100.9-125.2 (slow)
Q4 yes 200k 1008.7-1252.2 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 B50 run DistilProtBert?โ–ถ

Yes. At Q4 it generates ~1008.7-1252.2 tok/s and fits up to 200k 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 200k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.