// RUN — FITS

Can the Jetson Thor T3000 run Llama 3.2 11B?

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

Llama 3.2 11B on the Jetson Thor T3000

QuantFits?Max contextSpeedBeyond context
FP16 yes 37k 9.4-11.2 t/s ~0.3-0.4 (slow)
Q8 yes 102k 18.8-22.4 t/s ~0.7-0.8 (slow)
Q4 yes 130k 33.6-40 t/s ~1.2-1.5 (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 11B specs → Other hardware

FAQ

Can the Jetson Thor T3000 run Llama 3.2 11B?▶

Yes. At Q4 it generates ~33.6-40 tok/s and fits up to 130k context; beyond that it spills to SSD swap and slows to ~1.2-1.5 tok/s.

How much context fits?▶

At Q4, up to about 130k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.