// RUN — FITS

Can the Jetson Thor T2000 run Japanese-LM-3.6B?

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

Japanese-LM-3.6B on the Jetson Thor T2000

QuantFits?Max contextSpeedBeyond context
FP16 yes 87k 13.9-16.6 t/s ~1-1.2 (slow)
Q8 yes 142k 27.8-33.1 t/s ~2-2.4 (slow)
Q4 yes 166k 49.6-59.1 t/s ~3.6-4.3 (slow)

Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.

→ All models on the Jetson Thor T2000 → Japanese-LM-3.6B specs → Other hardware

FAQ

Can the Jetson Thor T2000 run Japanese-LM-3.6B?▶

Yes. At Q4 it generates ~49.6-59.1 tok/s and fits up to 166k context; beyond that it spills to SSD swap and slows to ~3.6-4.3 tok/s.

How much context fits?▶

At Q4, up to about 166k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.