Request a quoteBuy GPUs
HYPERCUBE
HYPERQ
GPUs
Astra Cybercity
Sectors
Press Room
Company

info@worldoneindia.netWhatsApp +91 93244 08321

Modular and factory scale

Prime Cell P72

One rack, one NVLink domain.

A complete rack-scale system in a twenty-foot module: seventy-two GPUs that work as one, with the coolant distribution, fabric, storage and power to run them. GB300 NVL72 today, Vera Rubin NVL72 in the Vera Rubin edition.

Illustrative exterior rendering of Prime Cell P72, shown in full.
72GPUs in one NVLink domain
1.44 EFFP4 sparse; 3.6 EF NVFP4 in the Vera Rubin edition
37 TBfast memory, GB300 edition
170 to 220 kWfacility envelope, GB300 edition

StatusGB300 NVL72 shipping, allocation constrained. Vera Rubin edition: production ramp, allocation and certification.

Questions first? Ask the team about Prime Cell P72

A closer look.

The whole rack-scale cell on one front line, beside its cooling package.

BrownfieldRack-scale capacity on a refurbished industrial estate: a new neighbour for an old works, with its own plant and a clear boundary.
The rack-scale cellOne NVL72 rack, its coolant distribution unit, a fabric rack, a storage rack and protected power. The rack position takes GB300 today and Vera Rubin next.
Inside the rack-scale cellOne rack-scale system beside its coolant unit, with the fabric and storage racks and the power cabinet beyond: the whole cell on one front line.

Styling concepts from the HYPERCUBE Product Family Design Collection, Edition 3. Configuration not finalised; renders do not depict a supplied configuration.

Two editions.

Blackwell Ultra today and Vera Rubin next, in the same module and the same layout.

SpecificationGB300 editionVera Rubin edition
RackGB300 NVL72Vera Rubin NVL72
GPUs72 Blackwell Ultra B30072 Rubin
CPUs36 Grace: 2,592 Arm Neoverse V2 cores36 Vera: 3,168 Arm cores
FP4 inference1.44 EF sparse3.6 EF NVFP4
FP4 dense or training1.08 EF dense2.5 EF NVFP4 training
FP8720 PFAbout 1.26 EF: 72 × 17.5 PF per GPU
GPU memory20 TB HBM3e at 576 TB/s20.7 TB HBM4 at 1.6 PB/s
CPU memory17 TB LPDDR5X at 14 TB/s54 TB LPDDR5X
NVLinkNVLink 5: 130 TB/s; 1.8 TB/s per GPUNVLink 6: 260 TB/s; 3.6 TB/s per GPU
Scale-out800 Gb/s per GPU, ConnectX-81.6 Tb/s per GPU, ConnectX-9
Rack power135 kW TDP; 155 kW peakAbout 190 to 230 kW, third-party figure
Facility170 to 220 kW envelopeAbout 220 to 280 kW, planning
CoolingLiquid: CDU and dry cooler100 per cent liquid at 45 °C inlet
Storage0.5 to 1.0 PB usable NVMe0.5 to 1.0 PB usable NVMe
StatusShipping; allocation constrainedProduction ramp; allocation and certification

Vera Rubin rack power is a third-party figure; NVIDIA has not published an official rack power. Vera Rubin FP8 is derived from NVIDIA's per-GPU figure. The facility range for Vera Rubin is a first-principles planning range, not an approved duty. Reference figures from the HYPERCUBE Product Family Design Collection, Edition 3, and NVIDIA published platform data. They are budgetary and indicative, not a supplier quotation. Final configuration, pricing, availability and delivery are confirmed by quotation for a named country and end user. Images are styling concepts.

What goes in.

One heat-rejection package beside the module. Vera Rubin's 45 °C water allows dry cooling in most climates.

Modules and packages

1 Twenty-foot module
6.06 × 2.44 × 2.90 m
1 Heat-rejection package
Dry cooler, 4.0 m long, beside the module

What the site provides

  • Low-voltage supply at 415 or 480 VAC, sized per edition
  • Fibre uplinks to the customer network
  • No water in operation: a closed liquid loop to a dry cooler
  • Concrete pad for the module and the package, crane access
ItemQtyWhat it is
Rack-scale systemNVL72118 compute trays of four GPUs and two CPUs, 9 NVLink switch trays and power shelves; GB300 NVL72 or Vera Rubin NVL72
GPUs and CPUs72 + 36One NVLink domain
Fabric rackF11Scale-out, management and out-of-band network
Storage rackS110.5 to 1.0 PB usable NVMe
Power cabinet and buswayU11Distribution and protection to the rack power shelves
Coolant distribution unit1Liquid-to-liquid exchanger and pumps, sized for the edition ordered
Controls panel1Building management, access control and monitoring
Clean-agent fire suppression2Cylinders with detection, beside the entrance
Heat-rejection packageT11Dry cooler outside the module

Options.

Chosen at quotation and fixed in the bill of materials for the edition ordered. Prices are given by quotation.

Compute

  • GB300 edition: one GB300 NVL72
  • Vera Rubin edition: one Vera Rubin NVL72 in the same MGX rack position
  • Plant pre-sized for the Vera Rubin transition

Storage

  • 0.5 or 1.0 PB usable NVMe
  • Immutable backup tier

Network

  • InfiniBand or Spectrum-X scale-out
  • 800 Gb/s per GPU today, 1.6 Tb/s per GPU with Vera Rubin
  • Out-of-band management network

Power and autonomy

  • UPS ride-through to the rack power shelves
  • 415 or 480 VAC; 800 VDC option for Vera Rubin
  • Single or dual utility feed

Cooling and climate

  • Dry cooler sized per edition and design ambient
  • Hot-climate package
  • Package in louvre fascia or sleeved finish

Security

  • Access control and CCTV
  • Customer-held encryption keys
  • Telemetry under customer control

Site and services

  • Factory, site and workload acceptance
  • Remote monitoring
  • In-country support and spares

Finish

  • Pearl white sleeve, the reference finish
  • Graphite sleeve with a white logo
  • Titanium-grey sleeve for coastal and industrial sites

Best fit.

Where Prime Cell P72 earns its place.

  1. National champions and large state enterprises
  2. Telecom AI capacity and enterprise AI services
  3. Large research institutes and simulation
  4. Rack-scale reasoning, training and high-concurrency inference

Price Prime Cell P72 for your site.

Tell us the quantity, the delivery country and the timing. We reply with a written quotation: price, lead time and delivery terms.

Developed by Quantum AI Connect, owner of HYPERCUBE and HYPERQ.
Prime Cell P7272 GPUs · Rack-scale AI module
Request a price