// RUN โ€” FITS

Can the Jetson Thor T2000 run ByT5-XXL?

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

ByT5-XXL on the Jetson Thor T2000

QuantFits?Max contextSpeedBeyond context
FP16 no โ€” โ€” โ€”
Q8 yes 0 7.8-9.2 t/s ~0.6-0.7 (slow)
Q4 yes 35k 13.8-16.5 t/s ~1-1.2 (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 ByT5-XXL?โ–ถ

Yes. At Q4 it generates ~13.8-16.5 tok/s and fits up to 35k context; beyond that it spills to SSD swap and slows to ~1-1.2 tok/s.

How much context fits?โ–ถ

At Q4, up to about 35k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.