// RUN โ€” FITS

Can the NVIDIA GeForce RTX 3090 Ti run Jiutian?

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

Jiutian on the NVIDIA GeForce RTX 3090 Ti

QuantFits?Max contextSpeedBeyond context
FP16 no โ€” โ€” โ€”
Q8 yes 41k 52.9-63.1 t/s ~2.1-2.5 (slow)
Q4 yes 78k 94.5-112.7 t/s ~3.8-4.5 (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 Ti run Jiutian?โ–ถ

Yes. At Q4 it generates ~94.5-112.7 tok/s and fits up to 78k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~3.8-4.5 tok/s.

How much context fits?โ–ถ

At Q4, up to about 78k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.