// RUN โ€” FITS

Can the Intel Arc Pro B50 run Phi-4 Mini?

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

Phi-4 Mini on the Intel Arc Pro B50

QuantFits?Max contextSpeedBeyond context
FP16 yes 86k 17.1-21.2 t/s ~3.1-3.8 (slow)
Q8 yes 144k 34.2-42.4 t/s ~6.1-7.6 (slow)
Q4 yes 169k 61.1-75.8 t/s ~10.9-13.5 (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 Phi-4 Mini?โ–ถ

Yes. At Q4 it generates ~61.1-75.8 tok/s and fits up to 169k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~10.9-13.5 tok/s.

How much context fits?โ–ถ

At Q4, up to about 169k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.