// RUN โ€” FITS

Can the Intel Arc Pro B70 run Spec-Drafter?

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

Spec-Drafter on the Intel Arc Pro B70

QuantFits?Max contextSpeedBeyond context
FP16 yes 411k 352.6-437.8 t/s ~23.2-28.8 (slow)
Q8 yes 419k 705.3-875.5 t/s ~46.4-57.6 (slow)
Q4 yes 422k 1259.4-1563.4 t/s ~82.9-102.9 (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 Spec-Drafter?โ–ถ

Yes. At Q4 it generates ~1259.4-1563.4 tok/s and fits up to 422k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~82.9-102.9 tok/s.

How much context fits?โ–ถ

At Q4, up to about 422k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.