// RUN โ€” FITS

Can the NVIDIA GeForce RTX 4070 Super run Pythia-1b?

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

Pythia-1b on the NVIDIA GeForce RTX 4070 Super

QuantFits?Max contextSpeedBeyond context
FP16 yes 115k 184-219.2 t/s ~14.6-17.4 (slow)
Q8 yes 130k 367.9-438.5 t/s ~29.2-34.8 (slow)
Q4 yes 137k 657-783 t/s ~52.1-62.1 (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 Super run Pythia-1b?โ–ถ

Yes. At Q4 it generates ~657-783 tok/s and fits up to 137k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~52.1-62.1 tok/s.

How much context fits?โ–ถ

At Q4, up to about 137k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.