// RUN โ€” FITS

Can the Intel Arc B580 12GB run LUKE?

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

LUKE on the Intel Arc B580 12GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 131k 273.8-339.9 t/s ~24-29.8 (slow)
Q8 yes 138k 547.6-679.8 t/s ~48-59.6 (slow)
Q4 yes 141k 977.8-1213.8 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 B580 12GB run LUKE?โ–ถ

Yes. At Q4 it generates ~977.8-1213.8 tok/s and fits up to 141k 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 141k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.