// RUN โ€” FITS

Can the NVIDIA GeForce RTX 3090 run Yi 6B?

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

Yi 6B on the NVIDIA GeForce RTX 3090

QuantFits?Max contextSpeedBeyond context
FP16 yes 65k 56.9-67.9 t/s ~2.4-2.9 (slow)
Q8 yes 111k 113.9-135.7 t/s ~4.9-5.8 (slow)
Q4 yes 131k 203.4-242.4 t/s ~8.7-10.4 (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 Yi 6B?โ–ถ

Yes. At Q4 it generates ~203.4-242.4 tok/s and fits up to 131k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~8.7-10.4 tok/s.

How much context fits?โ–ถ

At Q4, up to about 131k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.