// RUN โ€” FITS

Can the Intel Arc A770 16GB run S4?

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

S4 on the Intel Arc A770 16GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 194k 652.2-809.6 t/s ~46.6-57.8 (slow)
Q8 yes 198k 1304.4-1619.3 t/s ~93.2-115.7 (slow)
Q4 yes 200k 2329.3-2891.6 t/s ~166.4-206.5 (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 S4?โ–ถ

Yes. At Q4 it generates ~2329.3-2891.6 tok/s and fits up to 200k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~166.4-206.5 tok/s.

How much context fits?โ–ถ

At Q4, up to about 200k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.