// RUN โ€” FITS

Can the NVIDIA GeForce RTX 3090 run Stable Cascade?

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

Stable Cascade on the NVIDIA GeForce RTX 3090

QuantFits?Max contextSpeedBeyond context
FP16 yes 79k 66.7-79.5 t/s ~2.9-3.4 (slow)
Q8 yes 118k 133.5-159 t/s ~5.7-6.8 (slow)
Q4 yes 135k 238.3-284 t/s ~10.2-12.1 (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 NVIDIA GeForce RTX 3090 run Stable Cascade?โ–ถ

Yes. At Q4 it generates ~238.3-284 tok/s and fits up to 135k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~10.2-12.1 tok/s.

How much context fits?โ–ถ

At Q4, up to about 135k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.