// RUN โ€” FITS

Can the NVIDIA A100 PCIe 80GB run MinerU2.5?

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

MinerU2.5 on the NVIDIA A100 PCIe 80GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 1064k 588.6-701.4 t/s ~12.2-14.5 (slow)
Q8 yes 1082k 1177.1-1402.9 t/s ~24.3-29 (slow)
Q4 yes 1090k 2102-2505.1 t/s ~43.5-51.8 (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 A100 PCIe 80GB run MinerU2.5?โ–ถ

Yes. At Q4 it generates ~2102-2505.1 tok/s and fits up to 1090k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~43.5-51.8 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1090k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.