// RUN โ€” FITS

Can the NVIDIA GeForce RTX 3090 Ti 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 Ti

QuantFits?Max contextSpeedBeyond context
FP16 yes 65k 61.3-73.1 t/s ~2.4-2.9 (slow)
Q8 yes 111k 122.6-146.2 t/s ~4.9-5.8 (slow)
Q4 yes 131k 219-261 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 Ti run Yi 6B?โ–ถ

Yes. At Q4 it generates ~219-261 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.