// RUN โ€” FITS

Can the Jetson Thor T2000 run BEIT-3?

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

BEIT-3 on the Jetson Thor T2000

QuantFits?Max contextSpeedBeyond context
FP16 yes 139k 26.3-31.4 t/s ~1.9-2.3 (slow)
Q8 yes 168k 52.6-62.7 t/s ~3.8-4.6 (slow)
Q4 yes 181k 94-112 t/s ~6.9-8.2 (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 BEIT-3?โ–ถ

Yes. At Q4 it generates ~94-112 tok/s and fits up to 181k context; beyond that it spills to SSD swap and slows to ~6.9-8.2 tok/s.

How much context fits?โ–ถ

At Q4, up to about 181k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.