// RUN โ€” FITS

Can the NVIDIA GeForce RTX 4070 run KataGo?

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

KataGo on the NVIDIA GeForce RTX 4070

QuantFits?Max contextSpeedBeyond context
FP16 yes 145k 73584-87696 t/s ~5840-6960 (slow)
Q8 yes 146k 147168-175392 t/s ~11680-13920 (slow)
Q4 yes 146k 262800-313200 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 4070 run KataGo?โ–ถ

Yes. At Q4 it generates ~262800-313200 tok/s and fits up to 146k 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 146k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.