// RUN โ€” FITS

Can the NVIDIA B200 run Step 3.7 Flash?

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

Step 3.7 Flash on the NVIDIA B200

QuantFits?Max contextSpeedBeyond context
FP16 no โ€” โ€” โ€”
Q8 no โ€” โ€” โ€”
Q4 yes 123k 52.7-62.8 t/s ~0.3-0.3 (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 Step 3.7 Flash?โ–ถ

Yes. At Q4 it generates ~52.7-62.8 tok/s and fits up to 123k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~0.3-0.3 tok/s.

How much context fits?โ–ถ

At Q4, up to about 123k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.