// RUN โ€” FITS

Can the NVIDIA H100 PCIe 80GB run DNABERT?

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

DNABERT on the NVIDIA H100 PCIe 80GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 1097k 6636.4-7909.1 t/s ~132.7-158.2 (slow)
Q8 yes 1098k 13272.7-15818.2 t/s ~265.5-316.4 (slow)
Q4 yes 1099k 23701.3-28246.8 t/s ~474-564.9 (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 H100 PCIe 80GB run DNABERT?โ–ถ

Yes. At Q4 it generates ~23701.3-28246.8 tok/s and fits up to 1099k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~474-564.9 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1099k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.