// RUN โ€” FITS

Can the NVIDIA GeForce RTX 4070 Ti Super run Qwen2-Audio?

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

Qwen2-Audio on the NVIDIA GeForce RTX 4070 Ti Super

QuantFits?Max contextSpeedBeyond context
FP16 no โ€” โ€” โ€”
Q8 yes 38k 59.8-71.3 t/s ~3.6-4.2 (slow)
Q4 yes 66k 106.8-127.3 t/s ~6.4-7.6 (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 4070 Ti Super run Qwen2-Audio?โ–ถ

Yes. At Q4 it generates ~106.8-127.3 tok/s and fits up to 66k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~6.4-7.6 tok/s.

How much context fits?โ–ถ

At Q4, up to about 66k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.