// RUN โ€” FITS

Can the NVIDIA GeForce RTX 3090 run Stable Diffusion 3 Medium?

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

Stable Diffusion 3 Medium on the NVIDIA GeForce RTX 3090

QuantFits?Max contextSpeedBeyond context
FP16 yes 238k 136.7-162.9 t/s ~5.8-7 (slow)
Q8 yes 276k 273.3-325.7 t/s ~11.7-13.9 (slow)
Q4 yes 293k 488.1-581.7 t/s ~20.9-24.9 (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 3090 run Stable Diffusion 3 Medium?โ–ถ

Yes. At Q4 it generates ~488.1-581.7 tok/s and fits up to 293k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~20.9-24.9 tok/s.

How much context fits?โ–ถ

At Q4, up to about 293k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.