All insights

NVIDIA Vera Rubin: What UK Data Centres Need to Host It

NVIDIA Vera Rubin NVL72 racks can draw over 200kW and need 100% liquid cooling at up to 45°C. See what a UK data centre needs to host Vera Rubin.

NVIDIA Vera Rubin AI platform for next-generation data centres

NVIDIA Vera Rubin is NVIDIA's AI platform for 2026. Its flagship rack, the Vera Rubin NVL72, brings significant demands for UK data centres, including over 200kW of power per rack, 100% liquid cooling and facility water capable of reaching temperatures of up to 45°C.

This guide is for UK infrastructure leads and AI teams planning where to put Vera Rubin. It covers the published power and cooling numbers, how the platform compares with Blackwell, and what to ask a colocation provider before you sign.

Key takeaways

  • The NVIDIA Vera Rubin NVL72 rack holds 72 Rubin GPUs and 36 Vera CPUs, and is fully liquid-cooled with no fans in the compute trays.
  • A single Vera Rubin NVL72 rack can draw over 200kW, compared with roughly 120kW for a GB200 NVL72 rack.
  • NVIDIA designs Vera Rubin for coolant inlet temperatures up to 45°C, letting dry coolers reject heat without chillers.
  • Rubin Ultra in the Kyber rack is expected in 2027 at around 600kW per rack, so a hall built for Vera Rubin today should have a route to much higher densities.

What is NVIDIA Vera Rubin?

NVIDIA Vera Rubin is a rack-scale AI computing platform that pairs NVIDIA's Rubin GPU with its Vera CPU. It succeeds the Grace Blackwell generation and is built for training and running very large AI models. The name is shared with the American astronomer Vera Rubin and the Vera C. Rubin Observatory, which are unrelated to the hardware.

The main product is the Vera Rubin NVL72, a single rack of 72 Rubin GPUs and 36 Vera CPUs linked by sixth-generation NVLink. According to The Register's CES 2026 coverage, each rack carries 20.7TB of HBM4 GPU memory and 54TB of LPDDR5X across 18 compute blades and nine NVSwitch blades. Each Rubin GPU has 288GB of HBM4 and is rated by NVIDIA at 50 petaflops of NVFP4 inference. Even the smaller HGX Rubin NVL8 eight-GPU server now requires liquid cooling, so there is no air-cooled way into the Rubin generation.

Vera Rubin NVL72 specifications for data centre planning

The Vera Rubin NVL72 specifications that matter to a data centre are power and cooling, not petaflops. The figures below are the ones published by NVIDIA or reported by the technical press as of November 2026.

SpecificationVera Rubin NVL72What it means for the facility
GPUs and CPUs72 Rubin GPUs, 36 Vera CPUsOne rack is one 72-GPU NVLink domain
Rack powerCan exceed 200kWSeveral times a typical enterprise rack
CoolingFully liquid-cooled, fanless traysFacility water to every rack
Coolant inlet temperatureUp to 45°CDry coolers can replace chillers
Power architecture800VDC, fed from a power sidecar rackExtra rack positions for power equipment
GPU memory20.7TB HBM4 per rackNo facility impact, but shows the scale

NVIDIA revised several numbers between announcement and shipping. ServeTheHome reported in October 2026 that shipping Rubin GPUs run HBM4 bandwidth of 19.2TB/s rather than the 22TB/s first quoted, and that NVLink bandwidth for a full NVL72 rack is 216TB/s rather than 260TB/s. Plan around shipping specifications, not launch slides.

How much power does a Vera Rubin rack need?

A Vera Rubin NVL72 rack can draw more than 200kW. Tom's Hardware, reporting from NVIDIA's Engineering SuperLab in July 2026, wrote that a single rack "can easily consume over 200 kW". NVIDIA has not put a single-rack power figure on its own specification page, so treat 200kW as a floor for planning, not a ceiling.

That is a big step up from Blackwell. NVIDIA's guide for the DGX GB200 rack puts it at around 120kW, as we explain in what 120kW per rack looks like. At 400V three-phase and unity power factor, a 200kW rack requires roughly 290A before allowances. For comparison, a 120kW rack requires around 173A.

Vera Rubin also changes how power reaches the rack. NVIDIA is moving to 800VDC, and its current approach uses a power "sidecar": a separate rack of power equipment that takes 415V or 480V AC from the facility, converts it once to 800VDC and feeds the compute racks beside it. In practice, that means you need floor positions and power capacity for the sidecars as well as the compute racks.

What cooling does Vera Rubin need?

Vera Rubin needs direct liquid cooling to every compute tray, with no air-cooled fallback. The compute trays have no fans, and coolant enters through large pipework at the top of the rack and leaves at the bottom. Earlier GB200 and GB300 NVL72 racks used hybrid cooling, with some heat still removed by air.

Vera Rubin uses cold-plate direct liquid cooling. Cold plates sit directly on the GPUs and CPUs to remove heat. Manifolds distribute coolant throughout the rack, while a coolant distribution unit (CDU) separates the rack cooling loop from the facility water loop. This is the same architecture we run as direct-to-chip cooling for GPU estates, and our guide to what a coolant distribution unit does covers the basics.

CDU capacity has to be sized at hall level, not rack by rack. Supermicro's shipping Vera Rubin packages, as reported by StorageReview in September 2026, pair NVL72 racks with in-row CDUs rated at 1.8MW each, deployed with N+1 redundancy.

Immersion cooling is a strong fit for many dense GPU servers, and we offer single-phase immersion for those estates. Vera Rubin NVL72, however, is designed as a cold-plate rack with quick-connect manifolds, so it belongs in a direct-to-chip environment.

Why does 45°C water matter for UK data centres?

A 45°C coolant inlet temperature means a Vera Rubin hall can reject heat with dry coolers and no mechanical chillers. Tom's Hardware reported that if the coolant inlet temperature is 45°C or less, a heat exchanger can cool the whole system without chillers. Removing chillers cuts the energy spent on cooling, which improves power usage effectiveness (PUE).

The UK climate suits this design. The highest temperature ever recorded in the UK is 40.3°C, at Coningsby in Lincolnshire, verified by the Met Office in 2022. For almost all of the year, outside air is well below 45°C, giving dry coolers plenty of margin. Designers still need to size for the hottest days, because a dry cooler needs some temperature difference between the water and the air to work.

How does Vera Rubin compare with Blackwell and Rubin Ultra?

Vera Rubin takes rack power from around 120kW on Blackwell to over 200kW and goes fully liquid-cooled, and Rubin Ultra will push densities much higher again from 2027.

PlatformRack powerCoolingAvailability
GB200 NVL72 (Blackwell)Around 120kWHybrid liquid and airShipping
Vera Rubin NVL72Over 200kW100% liquid, up to 45°C inletRamping through late 2026
Rubin Ultra (Kyber rack)Around 600kWNew Kyber rack and cooling systemExpected 2027

The Rubin Ultra figure comes from The Register's reporting on NVIDIA's roadmap. For anyone signing a five-year colocation contract, the real question is whether the hall that takes Vera Rubin today can grow towards Kyber densities later.

Is Vera Rubin available yet?

AI computing infrastructure inside a modern data centre
AI computing infrastructure inside a modern data centre

Vera Rubin is shipping, with volume ramping through the final quarter of 2026. NVIDIA announced at CES in January 2026 that the platform was in full production, with systems expected in the second half of the year. ServeTheHome reported at the end of October 2026 that Rubin was mid-ramp and that hyperscalers were making some of the first NVL72 systems generally available, with much more to deploy "over the next few quarters".

For UK buyers, the hardware lead time may now be shorter than the time it takes to secure power. The UK government's AI Growth Zones policy paper sets out grid connection reforms aimed at cutting time to power for AI data centres by up to five years, which shows how long new connections can take.

What should you ask a UK colocation provider before deploying Vera Rubin?

Ask for specific numbers, in writing, on power, cooling and growth. A provider that cannot answer these questions clearly is not ready for Vera Rubin.

  1. Confirm the sustained power per rack, not the peak, and whether it is available now or depends on a future grid upgrade.
  2. Check the facility water temperature the loop is designed for. "Liquid cooling ready" does not always mean ready for 45°C.
  3. Ask how CDUs are sized and made redundant, for example N+1 at row or hall level.
  4. Ask about 800VDC sidecar racks and how many extra rack positions they need.
  5. Check floor loading and pipework routes for liquid-filled racks and manifolds.
  6. Ask about the upgrade path towards Rubin Ultra densities in 2027 and beyond.
  7. Check connectivity, because each NVL72 rack has 32.4TB/s of scale-out networking bandwidth and needs dense fibre to match.

Example: a UK AI start-up planning four Vera Rubin NVL72 racks should budget for at least 800kW of IT load for the compute racks alone, plus power sidecars, storage and networking. That fits within a single 1.8MW CDU on paper, but N+1 redundancy means at least two.

Can we host NVIDIA Vera Rubin?

Our AI-ready data centres are engineered for sustained densities of 50kW to 200kW per rack, with direct-to-chip and immersion cooling run by resident on-site engineers. Whether a specific Vera Rubin deployment fits depends on the rack count, the site and the power profile.

Frequently asked questions

Is NVIDIA Vera Rubin the same as the Vera Rubin Observatory?

No. NVIDIA Vera Rubin is an AI computing platform made up of the Rubin GPU and Vera CPU. The Vera C. Rubin Observatory is an astronomical observatory, and Vera Rubin was an American astronomer known for her work on dark matter. They share a name but have no technical connection.

What is the difference between Vera Rubin NVL144 and NVL72?

Vera Rubin NVL144 and NVL72 refer to the same rack. At GTC 2025, NVIDIA said it would count each GPU die rather than each package, which produced the NVL144 name. NVIDIA later dropped that plan, so the shipping rack is called Vera Rubin NVL72, with 72 Rubin GPU packages.

Can NVIDIA Vera Rubin be air-cooled?

No. The Vera Rubin NVL72 compute trays are fully liquid-cooled and have no fans, and even the smaller HGX Rubin NVL8 eight-GPU server requires liquid cooling. Any data centre hosting Vera Rubin needs direct liquid cooling with facility water delivered to the rack.

How much does it cost to host a Vera Rubin rack in the UK?

Modern data centre infrastructure with high-performance servers for AI computing
Modern data centre infrastructure with high-performance servers for AI computing

The cost of hosting a Vera Rubin rack depends on the power you reserve, the cooling infrastructure required, the contract length and the site. Reserved power is a major factor, so a rack drawing over 200kW is priced very differently from a standard rack.

Planning your Vera Rubin deployment

Hosting NVIDIA Vera Rubin comes down to three questions: can the site deliver well over 200kW per rack, can it run direct liquid cooling at up to 45°C, and can it grow towards Rubin Ultra densities? Put those questions to any provider early, because securing power can take longer than securing the hardware.

If you are sizing a Vera Rubin cluster for the UK, request a power assessment and our engineers will review your rack count, power profile and cooling needs with you.

Related articles

Data centre tiers explained: what Tier 3 and Tier 4 mean when you choose colocation.Data centre tiers explained: what Tier I to IV mean, how Tier 3 and Tier 4 differ, what the uptime percentages really are and how to check a tier claim.What is N+1 redundancy, and is it enough for your servers?What is N+1 redundancy? Understand how it protects servers, how it compares with 2N, its limits, and what to ask when choosing a colocation provider in the UK.What is PUE, and what does it mean for your colocation power bill?What is PUE? See how power usage effectiveness is calculated, what a good data centre PUE looks like and how it can influence your UK colocation power costs.UK vs US Data Centres: The Water Usage DifferenceHow UK and US data centres compare on water use: climate, cooling architecture, Thames Valley pressure, and where liquid cooling changes the equation.What Is AI Actually Used For?Four categories of AI workloads, where they run in the UK, and what each one actually demands of the data centre underneath. Written for infrastructure buyers.How Does Colocation Work?Colocation works by moving your own servers, storage and networking equipment into a professionally managed data centre. You continue to own and control…A Guide to Server Rack Sizes for Data CentresServer rack sizes are usually described in rack units, or U. One rack unit provides 1.75 inches, or 44.45 mm, of vertical mounting space, while most…How to Improve Network Latency in ColocationTo improve network latency in colocation, start by measuring where the delay actually occurs. Establish normal round-trip times, trace the routes between…Increasing Server Capacity Without Creating a New BottleneckIncreasing server capacity is not simply a matter of adding more CPU, memory or another server. The first step is identifying what is actually limiting…Data Centre Migration Checklist - How to Plan a Low-Risk MoveUse this data centre migration checklist to plan dependencies, power, connectivity, rollback and validation for a lower-risk move.How Much Does Immersion Cooling Cost? Capex, Opex, and TCO ExplainedSee what drives immersion cooling cost in the UK, from CapEx and OpEx to TCO, and compare the real cost of supporting high-density compute.What Is a Coolant Distribution Unit? A Data Centre CDU GuideWhat is a coolant distribution unit? Learn how CDUs manage coolant flow, heat transfer, and pressure in liquid-cooled data centres.AI Colocation in the UK: How to Choose Infrastructure That Will Not Hold Your GPUs BackCarbon-Z delivers AI colocation in the UK with liquid cooling up to 120kW per rack. Built for GPU clusters, AI training, and sustained high-density workloads.From 8kW To 120kW: When Your GPU Cluster Outgrows Standard ColocationGPU clusters scaling from 8kW to 120kW often outgrow standard colocation. Learn the warning signs and what infrastructure changes are needed for dense compute.Liquid Cooling For Data Centres: A Buyer's GuideLiquid Cooling for Data Centres explained. Compare cooling options, buyer checks and key questions before planning high-density infrastructure.What 120kW Per Rack Actually Looks Like: Power, Cooling, And Cabling SpecificationsSee what 120kW per rack means for power, cooling, cabling and monitoring before planning high-density data centre infrastructure.Are Colocation Data Centres the Same as Servers?Colocation data centres and servers fill different roles in IT infrastructure. Learn how each works, when colocation is the right choice and what to look for.Carrier-Neutral Data Centre Benefits: Why Network Choice MattersExplore carrier-neutral data centre benefits, from provider choice and route diversity to stronger hybrid connectivity.What Is Immersion Cooling? A Practical Guide for High-Density InfrastructureWhat is immersion cooling? Learn how it works, when it makes sense, and how it supports high-density infrastructure.How to Improve Network Resilience in Data CentresHow to improve network resilience in data centres through diverse connectivity, tested failover, configuration control and wider observability.Where to Colocate in the UK: A Guide to the Top Data Centre HubsChoosing a UK colocation hub now turns on power and cooling, not postcode. We map the four hub types and how to match each to your workload.Why AI and HPC Workloads Need Immersion CoolingAI and HPC racks now draw 40 to 140 kilowatts. We explain why air cooling has hit its ceiling and where immersion genuinely earns its place.What Does It Actually Cost to Run an AI Model?Running an AI model costs more than most organisations expect. We break down GPU hardware, power, cooling, and egress to show where the money actually goes.What Is Colocation? The Complete UK Guide 2026UK colocation services explained: costs, cooling, security, cloud comparisons and how to choose a provider. Written by engineers who run the facilities.Air Cooling vs Liquid Cooling: Which Does Your Infrastructure Actually Need?Air cooling vs liquid cooling: which does your infrastructure need? We break down rack density, PUE, and total cost to help you make the right call.Colocation vs Cloud - Where Your Workloads Actually BelongColocation vs cloud isn't a philosophy debate. We break down the real cost, compliance, and performance factors that determine where your workloads belong.The thirst for AIAI is revolutionary in its capabilities. It is becoming integrated to all the applications that we use…Combating obsolete Data CentresDive into how immersion cooling slashes energy use and unlocks high rack densities for AI, GPU and HPC workloads.Open DayExciting News! Join us for a Journey into the Future of Hosting and Cooling at Swindon Data Centre Open Day!AtomsCarbon-Z Atoms are modular, build-on-demand data centre units with up to 1MW capacity and flexible cooling options built for rapid deployment and scalability.

Ready to upgrade your infrastructure?

Stop overpaying for legacy efficiency. Get a quote for colocation, immersion or a custom build in under 24 hours.

Trusted by tiered vendors

Midas Immersion logoVirgin Media Business logoSubmer logoIntel logoWifinity logoValvoline Global logo
Call