// RUN โ€” FITS

Can the Intel Arc A770 16GB run LUKE?

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

LUKE on the Intel Arc A770 16GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 187k 336.2-417.4 t/s ~24-29.8 (slow)
Q8 yes 194k 672.5-834.8 t/s ~48-59.6 (slow)
Q4 yes 198k 1200.8-1490.7 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 A770 16GB run LUKE?โ–ถ

Yes. At Q4 it generates ~1200.8-1490.7 tok/s and fits up to 198k 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 198k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.