// RUN โ€” FITS

Can the Jetson Thor T2000 run ESM2-150M?

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

ESM2-150M on the Jetson Thor T2000

QuantFits?Max contextSpeedBeyond context
FP16 yes 192k 333.4-397.3 t/s ~24.3-29 (slow)
Q8 yes 195k 666.7-794.6 t/s ~48.7-58 (slow)
Q4 yes 196k 1190.6-1418.9 t/s ~86.9-103.6 (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 ESM2-150M?โ–ถ

Yes. At Q4 it generates ~1190.6-1418.9 tok/s and fits up to 196k context; beyond that it spills to SSD swap and slows to ~86.9-103.6 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.