// RUN โ€” FITS

Can the Intel Arc Pro B70 run LUKE?

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

LUKE on the Intel Arc Pro B70

QuantFits?Max contextSpeedBeyond context
FP16 yes 412k 365.1-453.2 t/s ~24-29.8 (slow)
Q8 yes 419k 730.1-906.3 t/s ~48-59.6 (slow)
Q4 yes 422k 1303.8-1618.5 t/s ~85.8-106.5 (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 LUKE?โ–ถ

Yes. At Q4 it generates ~1303.8-1618.5 tok/s and fits up to 422k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~85.8-106.5 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.