// RUN — FITS

Can the Jetson Thor T3000 run Llama 3.2 3B?

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

Llama 3.2 3B on the Jetson Thor T3000

QuantFits?Max contextSpeedBeyond context
FP16 yes 319k 31-37 t/s ~1.1-1.4 (slow)
Q8 yes 368k 62.1-74 t/s ~2.3-2.7 (slow)
Q4 yes 389k 110.9-132.1 t/s ~4.1-4.8 (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 T3000 → Llama 3.2 3B specs → Other hardware

FAQ

Can the Jetson Thor T3000 run Llama 3.2 3B?▶

Yes. At Q4 it generates ~110.9-132.1 tok/s and fits up to 389k context; beyond that it spills to SSD swap and slows to ~4.1-4.8 tok/s.

How much context fits?▶

At Q4, up to about 389k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.