// RUN โ€” FITS

Can the Intel Arc A770 16GB run Stable Cascade?

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

Stable Cascade on the Intel Arc A770 16GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 23k 31.7-39.4 t/s ~2.3-2.8 (slow)
Q8 yes 62k 63.4-78.8 t/s ~4.5-5.6 (slow)
Q4 yes 79k 113.3-140.6 t/s ~8.1-10 (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 Stable Cascade?โ–ถ

Yes. At Q4 it generates ~113.3-140.6 tok/s and fits up to 79k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~8.1-10 tok/s.

How much context fits?โ–ถ

At Q4, up to about 79k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.