// RUN — FITS

Can the Jetson Thor T2000 run Llama-3.1-Minitron-4B?

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

Llama-3.1-Minitron-4B on the Jetson Thor T2000

QuantFits?Max contextSpeedBeyond context
FP16 yes 75k 12.5-14.9 t/s ~0.9-1.1 (slow)
Q8 yes 136k 25-29.8 t/s ~1.8-2.2 (slow)
Q4 yes 163k 44.6-53.2 t/s ~3.3-3.9 (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 → Llama-3.1-Minitron-4B specs → Other hardware

FAQ

Can the Jetson Thor T2000 run Llama-3.1-Minitron-4B?▶

Yes. At Q4 it generates ~44.6-53.2 tok/s and fits up to 163k context; beyond that it spills to SSD swap and slows to ~3.3-3.9 tok/s.

How much context fits?▶

At Q4, up to about 163k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.