// RUN โ€” FITS

Can the Intel Arc Pro B50 run Domyn Small?

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

Domyn Small on the Intel Arc Pro B50

QuantFits?Max contextSpeedBeyond context
FP16 no โ€” โ€” โ€”
Q8 yes 20k 13-16.1 t/s ~2.3-2.9 (slow)
Q4 yes 47k 23.2-28.8 t/s ~4.1-5.1 (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 Domyn Small?โ–ถ

Yes. At Q4 it generates ~23.2-28.8 tok/s and fits up to 47k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~4.1-5.1 tok/s.

How much context fits?โ–ถ

At Q4, up to about 47k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.