// RUN โ€” FITS

Can the Intel Arc Pro B50 run T5-11B?

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

T5-11B on the Intel Arc Pro B50

QuantFits?Max contextSpeedBeyond context
FP16 no โ€” โ€” โ€”
Q8 yes 14k 11.8-14.7 t/s ~2.1-2.6 (slow)
Q4 yes 43k 21.1-26.2 t/s ~3.8-4.7 (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 T5-11B?โ–ถ

Yes. At Q4 it generates ~21.1-26.2 tok/s and fits up to 43k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~3.8-4.7 tok/s.

How much context fits?โ–ถ

At Q4, up to about 43k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.