// RUN โ€” FITS

Can the Jetson Thor T3000 run Gemma 3 270M?

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

Gemma 3 270M on the Jetson Thor T3000

QuantFits?Max contextSpeedBeyond context
FP16 yes 408k 369.1-439.8 t/s ~13.5-16.1 (slow)
Q8 yes 412k 738.1-879.7 t/s ~27-32.2 (slow)
Q4 yes 414k 1318.1-1570.8 t/s ~48.3-57.5 (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 T3000 run Gemma 3 270M?โ–ถ

Yes. At Q4 it generates ~1318.1-1570.8 tok/s and fits up to 414k context; beyond that it spills to SSD swap and slows to ~48.3-57.5 tok/s.

How much context fits?โ–ถ

At Q4, up to about 414k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.