// RUN โ€” FITS

Can the NVIDIA GeForce RTX 3080 10GB run Stable Diffusion 3.5 Medium?

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

Stable Diffusion 3.5 Medium on the NVIDIA GeForce RTX 3080 10GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 41k 111-132.2 t/s ~5.8-7 (slow)
Q8 yes 79k 221.9-264.5 t/s ~11.7-13.9 (slow)
Q4 yes 96k 396.3-472.3 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 3080 10GB run Stable Diffusion 3.5 Medium?โ–ถ

Yes. At Q4 it generates ~396.3-472.3 tok/s and fits up to 96k 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 96k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.