// RUN โ€” FITS

Can the NVIDIA H100 PCIe 80GB run Minitron 8B?

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

Minitron 8B on the NVIDIA H100 PCIe 80GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 423k 88-104.8 t/s ~1.8-2.1 (slow)
Q8 yes 487k 175.9-209.6 t/s ~3.5-4.2 (slow)
Q4 yes 515k 314.1-374.4 t/s ~6.3-7.5 (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 Minitron 8B?โ–ถ

Yes. At Q4 it generates ~314.1-374.4 tok/s and fits up to 515k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~6.3-7.5 tok/s.

How much context fits?โ–ถ

At Q4, up to about 515k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.