// RUN โ€” FITS

Can the NVIDIA B200 run S4?

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

S4 on the NVIDIA B200

QuantFits?Max contextSpeedBeyond context
FP16 yes 2665k 11726.9-13975.9 t/s ~58.6-69.9 (slow)
Q8 yes 2669k 23453.8-27951.8 t/s ~117.3-139.8 (slow)
Q4 yes 2670k 41881.8-49913.9 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 B200 run S4?โ–ถ

Yes. At Q4 it generates ~41881.8-49913.9 tok/s and fits up to 2670k 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 2670k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.