// RUN โ€” FITS

Can the NVIDIA GeForce RTX 3090 run S4?

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

S4 on the NVIDIA GeForce RTX 3090

QuantFits?Max contextSpeedBeyond context
FP16 yes 306k 1372-1635.2 t/s ~58.6-69.9 (slow)
Q8 yes 310k 2744.1-3270.4 t/s ~117.3-139.8 (slow)
Q4 yes 312k 4900.2-5839.9 t/s ~209.4-249.6 (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 3090 run S4?โ–ถ

Yes. At Q4 it generates ~4900.2-5839.9 tok/s and fits up to 312k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~209.4-249.6 tok/s.

How much context fits?โ–ถ

At Q4, up to about 312k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.