// RUN โ€” FITS

Can the NVIDIA GeForce RTX 5090 run NASA SMD?

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

NASA SMD on the NVIDIA GeForce RTX 5090

QuantFits?Max contextSpeedBeyond context
FP16 yes 423k 5232.6-6236.2 t/s ~116.8-139.2 (slow)
Q8 yes 424k 10465.3-12472.3 t/s ~233.6-278.4 (slow)
Q4 yes 425k 18688-22272 t/s ~417.1-497.1 (slow)

Estimate (memory-bound). Beyond "max context" the KV cache spills to system RAM offload (depends on your system RAM) and speed drops to the "beyond" figure.

FAQ

Can the NVIDIA GeForce RTX 5090 run NASA SMD?โ–ถ

Yes. At Q4 it generates ~18688-22272 tok/s and fits up to 425k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~417.1-497.1 tok/s.

How much context fits?โ–ถ

At Q4, up to about 425k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.