// RUN — FITS

Can the Jetson Thor T2000 run GLA Transformer 340M?

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

GLA Transformer 340M on the Jetson Thor T2000

QuantFits?Max contextSpeedBeyond context
FP16 yes 186k 147.1-175.3 t/s ~10.7-12.8 (slow)
Q8 yes 192k 294.1-350.6 t/s ~21.5-25.6 (slow)
Q4 yes 194k 525.3-626 t/s ~38.3-45.7 (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 → GLA Transformer 340M specs → Other hardware

FAQ

Can the Jetson Thor T2000 run GLA Transformer 340M?▶

Yes. At Q4 it generates ~525.3-626 tok/s and fits up to 194k context; beyond that it spills to SSD swap and slows to ~38.3-45.7 tok/s.

How much context fits?▶

At Q4, up to about 194k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.