// RUN โ€” FITS

Can the Intel Arc Pro B70 run MegaMolBART?

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

MegaMolBART on the Intel Arc Pro B70

QuantFits?Max contextSpeedBeyond context
FP16 yes 425k 3918.2-4864 t/s ~257.8-320 (slow)
Q8 yes 426k 7836.4-9728 t/s ~515.6-640 (slow)
Q4 yes 426k 13993.7-17371.4 t/s ~920.6-1142.9 (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 B70 run MegaMolBART?โ–ถ

Yes. At Q4 it generates ~13993.7-17371.4 tok/s and fits up to 426k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~920.6-1142.9 tok/s.

How much context fits?โ–ถ

At Q4, up to about 426k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.