// RUN โ€” FITS

Can the NVIDIA RTX PRO 6000 Blackwell run HyenaDNA?

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

HyenaDNA on the NVIDIA RTX PRO 6000 Blackwell

QuantFits?Max contextSpeedBeyond context
FP16 yes 1325k 99103-118109.1 t/s ~2212.1-2636.4 (slow)
Q8 yes 1325k 198206.1-236218.2 t/s ~4424.2-5272.7 (slow)
Q4 yes 1325k 353939.4-421818.2 t/s ~7900.4-9415.6 (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 RTX PRO 6000 Blackwell run HyenaDNA?โ–ถ

Yes. At Q4 it generates ~353939.4-421818.2 tok/s and fits up to 1325k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~7900.4-9415.6 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1325k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.