// RUN โ€” FITS

Can the Intel Arc Pro B50 run HiFi - NN?

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

HiFi - NN on the Intel Arc Pro B50

QuantFits?Max contextSpeedBeyond context
FP16 yes 202k 21653.3-26880 t/s ~3866.7-4800 (slow)
Q8 yes 202k 43306.7-53760 t/s ~7733.3-9600 (slow)
Q4 yes 202k 77333.3-96000 t/s ~13809.5-17142.9 (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 HiFi - NN?โ–ถ

Yes. At Q4 it generates ~77333.3-96000 tok/s and fits up to 202k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~13809.5-17142.9 tok/s.

How much context fits?โ–ถ

At Q4, up to about 202k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.