Configure your RTX PRO 6000 Server Edition
Blackwell serving power — 96 GB per card, up to 4× in a 4U rack node.
Looking for a different storage solution? Contact us. The default is intentionally barebones and not application-specific.
Custom CPU, board, or beyond-max memory? Talk to sales →
Price
our landed cost — component prices updated Jun 2026Hardware at cost. We make 5% on the build. While your machine pays itself off we keep 70% of what it earns — once it's yours, you keep 70%.
What it runs
Blackwell silicon — a whole 70B fits on one 96 GB card, the serving sweet spot.
1.8 TB/s bandwidth — ample for large-model inference and render scenes.
Server barebones or a workstation board, with chassis, PSUs, and cooling matched to the card count.
Sized to feed every GPU without a data-loading bottleneck; the exact part scales with card count.
Blower-style cards in a tuned airflow path, monitored 24/7.
Sized for sustained multi-GPU serving load.
The RTX PRO 6000 pairs 96 GB of GDDR7 with Blackwell's render and AI cores — a whole Llama 70B fits on one card. Great for inference and serving (no NVLink, so not for large multi-GPU training — that's the H200's job). B3-IQ hand-builds this edition as a 4U rack node, up to 4× per node, hosted in Oregon; the 4× config is rent-to-own.
Hand-built & hosted in Eugene, Oregon · ~90% carbon-free hydro · monitored 24/7 · 6–8 weeks lead time.