// RUN โ€” FITS

Can the AMD Radeon RX 7900 XT run Stable Cascade?

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

Stable Cascade on the AMD Radeon RX 7900 XT

QuantFits?Max contextSpeedBeyond context
FP16 yes 51k 49.2-60.2 t/s ~2.5-3 (slow)
Q8 yes 90k 98.4-120.3 t/s ~4.9-6 (slow)
Q4 yes 107k 175.8-214.8 t/s ~8.8-10.7 (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 AMD Radeon RX 7900 XT run Stable Cascade?โ–ถ

Yes. At Q4 it generates ~175.8-214.8 tok/s and fits up to 107k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~8.8-10.7 tok/s.

How much context fits?โ–ถ

At Q4, up to about 107k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.