SSP, Strategic Supply Partners Live inventory
The desk
GPU procurementNodes and clusters, landed to your rack ● Live inventoryVerified lines, indicative pricing
By platform
B300 and GB300Current-generation Blackwell H200 and H100New stock and fleet rotation All platformsThe full catalogue
Rest of the stack
Memory, servers and storageThe kit around the accelerators Networking and opticsTransceivers, switching, cabling
Capacity without capex
GPU-as-a-serviceReserved, committed spend, on demand Bare-metal leasingDedicated clusters on a term
Decide first
Cloud vs bare metalWhere each one actually wins Reserved vs on demandThe break-even, calculated Cluster cost calculatorThe whole bill, not the GPU line
Space and power
Colocation and powerSingle racks to 100 MW Above 40 kW per rackWhere the shortlist collapses
Where
United States Europe Asia Pacific Middle East and Africa All regions →
Supply side
Have capacity to fill?Tell us what you hold
Analysis
InsightsWhat things cost, with the numbers Sizing guidesMemory, nodes, power, cost ComparisonsBuy, lease or rent
Start here
How an engagement worksThe first week, held to dates Find your fitThree questions, the right desk Glossary
Talk to the desk
Blackwell (Grace superchip) · 72 Blackwell GPUs + 36 Grace CPUs · Rack-scale NVL72

Buy NVIDIA GB200 NVL72 systems.

Currently unavailable. The listed NVIDIA GB200 line has sold through; the figures on this page are for reference. Ask the desk to source it or see what is live.

Verified allocation through the authorised channel, indicative direct pricing, landed anywhere the compliance file clears. You transact on the supplier's direct terms; our compensation sits on the supply side.

Check availability Find your fitAcknowledged within one hour, first sourcing pass within one business day.
The desk view

Where the NVIDIA GB200 NVL72 fits.

GB200 NVL72 is rack-scale computing: seventy-two Blackwell GPUs and thirty-six Grace CPUs behaving as one giant accelerator over NVLink. For the largest training and inference jobs it changes what a single deployment can do, and it changes what a facility must provide: this is liquid-cooled, high-density territory only.

We source NVL72 racks on requirement and currently hold a verified GB200 superchip system for teams building toward the architecture.

NVIDIA GB200 NVL72
Availability

What is verified today.

In the channel nowGB200 Dell superchip system, new, US located
Indicative price$158,000 per 2x GB200 system
Lead time7 days

Every line verified with the holder. Full list on the live inventory; pricing is indicative, ex-works USD, and moves with volume and term.

Straight answers

Asked first, answered straight.

What does an NVL72 rack require from the data centre?

Liquid cooling and rack power far beyond legacy norms. The facility question comes first, and the list of buildings that genuinely qualify is short. We name them.

Is GB200 right for inference?

For the largest models, emphatically: the NVL72's unified memory domain is built for exactly that. For ordinary production inference it is far more machine than needed.

How is rack-scale procured differently?

As an integrated system with the facility, power, cooling and commissioning inside the deal, not as parts. One accountable line matters more here than anywhere else in the catalogue.

Talk to the desk

Working through this on a real requirement?

Twenty minutes with the desk, no pitch and no quote at the end of it. Tell us roughly what you need and we will come back within one business day.

Acknowledged within one hour, first sourcing pass within one business day.
✓

Sent. We are on it.

Your enquiry has landed with the desk. Acknowledged within one hour.