// RUN โ€” FITS

Can the NVIDIA RTX PRO 6000 Blackwell run Ankh_base?

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

Ankh_base on the NVIDIA RTX PRO 6000 Blackwell

QuantFits?Max contextSpeedBeyond context
FP16 yes 1302k 883.9-1053.4 t/s ~19.7-23.5 (slow)
Q8 yes 1313k 1767.8-2106.8 t/s ~39.5-47 (slow)
Q4 yes 1318k 3156.8-3762.2 t/s ~70.5-84 (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 Ankh_base?โ–ถ

Yes. At Q4 it generates ~3156.8-3762.2 tok/s and fits up to 1318k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~70.5-84 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1318k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.