// RUN โ€” FITS

Can the NVIDIA GeForce RTX 3070 run KataGo?

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

KataGo on the NVIDIA GeForce RTX 3070

QuantFits?Max contextSpeedBeyond context
FP16 yes 89k 65408-77952 t/s ~5840-6960 (slow)
Q8 yes 89k 130816-155904 t/s ~11680-13920 (slow)
Q4 yes 89k 233600-278400 t/s ~20857.1-24857.1 (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 3070 run KataGo?โ–ถ

Yes. At Q4 it generates ~233600-278400 tok/s and fits up to 89k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~20857.1-24857.1 tok/s.

How much context fits?โ–ถ

At Q4, up to about 89k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.