// RUN โ€” FITS

Can the NVIDIA RTX PRO 6000 Blackwell run Surya?

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

Surya on the NVIDIA RTX PRO 6000 Blackwell

QuantFits?Max contextSpeedBeyond context
FP16 yes 1314k 1787.1-2129.8 t/s ~39.9-47.5 (slow)
Q8 yes 1319k 3574.2-4259.7 t/s ~79.8-95.1 (slow)
Q4 yes 1322k 6382.5-7606.6 t/s ~142.5-169.8 (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 Surya?โ–ถ

Yes. At Q4 it generates ~6382.5-7606.6 tok/s and fits up to 1322k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~142.5-169.8 tok/s.

How much context fits?โ–ถ

At Q4, up to about 1322k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.