// RUN โ€” FITS

Can the Jetson Thor T2000 run Pythia-410m?

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

Pythia-410m on the Jetson Thor T2000

QuantFits?Max contextSpeedBeyond context
FP16 yes 184k 122-145.4 t/s ~8.9-10.6 (slow)
Q8 yes 191k 243.9-290.7 t/s ~17.8-21.2 (slow)
Q4 yes 193k 435.6-519.1 t/s ~31.8-37.9 (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 Pythia-410m?โ–ถ

Yes. At Q4 it generates ~435.6-519.1 tok/s and fits up to 193k context; beyond that it spills to SSD swap and slows to ~31.8-37.9 tok/s.

How much context fits?โ–ถ

At Q4, up to about 193k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.