// RUN โ€” FITS

Can the Jetson Thor T2000 run Stable Cascade?

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

Stable Cascade on the Jetson Thor T2000

QuantFits?Max contextSpeedBeyond context
FP16 yes 20k 9.8-11.6 t/s ~0.7-0.8 (slow)
Q8 yes 59k 19.5-23.3 t/s ~1.4-1.7 (slow)
Q4 yes 77k 34.9-41.6 t/s ~2.5-3 (slow)

Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.

FAQ

Can the Jetson Thor T2000 run Stable Cascade?โ–ถ

Yes. At Q4 it generates ~34.9-41.6 tok/s and fits up to 77k context; beyond that it spills to SSD swap and slows to ~2.5-3 tok/s.

How much context fits?โ–ถ

At Q4, up to about 77k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.