// RUN โ€” FITS

Can the NVIDIA RTX PRO 6000 Blackwell run FoundationStereo?

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

FoundationStereo on the NVIDIA RTX PRO 6000 Blackwell

QuantFits?Max contextSpeedBeyond context
FP16 yes 1315k 1950.7-2324.8 t/s ~43.5-51.9 (slow)
Q8 yes 1320k 3901.5-4649.7 t/s ~87.1-103.8 (slow)
Q4 yes 1322k 6966.9-8303 t/s ~155.5-185.3 (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 FoundationStereo?โ–ถ

Yes. At Q4 it generates ~6966.9-8303 tok/s and fits up to 1322k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~155.5-185.3 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.