// RUN โ€” FITS

Can the NVIDIA GeForce RTX 5070 Ti run MinerU2.5?

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

MinerU2.5 on the NVIDIA GeForce RTX 5070 Ti

QuantFits?Max contextSpeedBeyond context
FP16 yes 165k 272.5-324.8 t/s ~12.2-14.5 (slow)
Q8 yes 183k 545.1-649.6 t/s ~24.3-29 (slow)
Q4 yes 191k 973.3-1160 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 GeForce RTX 5070 Ti run MinerU2.5?โ–ถ

Yes. At Q4 it generates ~973.3-1160 tok/s and fits up to 191k 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 191k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.