// RUN โ€” FITS

Can the Intel Arc Pro B50 run FRED-T5-XL?

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

FRED-T5-XL on the Intel Arc Pro B50

QuantFits?Max contextSpeedBeyond context
FP16 yes 149k 37.3-46.3 t/s ~6.7-8.3 (slow)
Q8 yes 175k 74.7-92.7 t/s ~13.3-16.6 (slow)
Q4 yes 187k 133.3-165.5 t/s ~23.8-29.6 (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 FRED-T5-XL?โ–ถ

Yes. At Q4 it generates ~133.3-165.5 tok/s and fits up to 187k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~23.8-29.6 tok/s.

How much context fits?โ–ถ

At Q4, up to about 187k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.