// RUN โ€” FITS

Can the Jetson Thor T2000 run MSA Transformer?

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

MSA Transformer on the Jetson Thor T2000

QuantFits?Max contextSpeedBeyond context
FP16 yes 194k 500.1-596 t/s ~36.5-43.5 (slow)
Q8 yes 195k 1000.1-1191.9 t/s ~73-87 (slow)
Q4 yes 196k 1785.9-2128.4 t/s ~130.4-155.4 (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 MSA Transformer?โ–ถ

Yes. At Q4 it generates ~1785.9-2128.4 tok/s and fits up to 196k context; beyond that it spills to SSD swap and slows to ~130.4-155.4 tok/s.

How much context fits?โ–ถ

At Q4, up to about 196k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.