// RUN โ€” FITS

Can the NVIDIA GeForce RTX 4090 run XGen-7B?

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

XGen-7B on the NVIDIA GeForce RTX 4090

QuantFits?Max contextSpeedBeyond context
FP16 yes 55k 54.9-65.4 t/s ~2.2-2.6 (slow)
Q8 yes 106k 109.8-130.9 t/s ~4.4-5.2 (slow)
Q4 yes 128k 196.1-233.7 t/s ~7.8-9.3 (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 4090 run XGen-7B?โ–ถ

Yes. At Q4 it generates ~196.1-233.7 tok/s and fits up to 128k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~7.8-9.3 tok/s.

How much context fits?โ–ถ

At Q4, up to about 128k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.