Platform

Vera Rubin, delivered as a service.

Liquidata builds on NVIDIA's Vera Rubin platform and delivers it as dedicated, managed clusters on powered sites, with the network, storage, monitoring, security and operations around it.

Vera Rubin NVL72
72 Rubin GPUs
36 Vera CPUs
3,600 PFLOPS NVFP4
20.7 TB HBM4
45 °C inlet water
~190 kW per rack
In full production since January 2026
Vera Rubin NVL72

One rack, seventy-two GPUs, one liquid loop.

The Vera Rubin NVL72 rack pairs 72 Rubin GPUs with 36 Vera CPUs over NVLink, cooled entirely by liquid with 45 °C inlet water, which allows cooling without chillers in most climates. NVIDIA reports the platform in full production since January 2026, with partner availability in the second half of 2026.

SpecificationPer NVL72 rackNote
GPUs and CPUs72 Rubin GPUs, 36 Vera CPUsOne NVLink domain
NVFP4 inference3,600 PFLOPSNVIDIA published figure
FP8 training1,260 PFLOPSNVIDIA published figure
HBM4 memory20.7 TB, 1,400 TB/s288 GB per GPU
NVLink bandwidth216 TB/sGPU to GPU
CPU memoryUp to 54 TB LPDDR5XVera CPUs
Cooling100% liquid, 45 °C inletChiller-free in most climates
Rack powerAbout 190 kWNVIDIA's standard setting; up to about 230 kW at maximum performance
Module calculator

Size a module in racks. Read it in megawatts.

Modules are contracted in racks and delivered against a site's power. Move the slider to see what a module needs from the site and the grid.

50racks

190 kW per rack at NVIDIA's standard setting plus 5% for scale-out network and storage; 8,760 hours a year; 288 GB HBM4 per GPU.

3,600
Rubin GPUs
1,036.8 TB
HBM4 memory
10.0 MW
IT load
12.5 MW
Facility load at design PUE
109,200 MWh
Electricity a year
80 h
Hours a 1,000 MWh storage station carries the module
What a module includes

The cluster, and everything that keeps it earning.

Design

Cluster design and bring-up

Rack layout, power and cooling integration with the site, fabric topology, burn-in and acceptance against the customer's workloads.

Fabric and storage

High-speed fabric and storage

Scale-out networking and storage sized to the workload, delivered with the module and operated as part of the service.

Software

Monitoring, diagnostics and remote operations

Liquidata's own monitoring software: cooling energy, availability, density and component health, with remote operations from day one.

Security

Security from site to tenant

Physical, network and tenant isolation designed in, for customers whose data and models cannot leave their jurisdiction.

Operations

Round-the-clock operations

Operations, service levels and support carried by Liquidata as the provider of record.

Energy

Energy-aware scheduling

Suitable workloads scheduled around renewable output, storage and prices at sites that have them, without touching service levels for the rest.

How Capacity is contracted

Reserved, then built, then delivered on the site's date.

Commitments of 12 to 36 months. Capacity is reserved on take-or-pay terms, priced for the term and the module, with Liquidata as provider of record.

Modules are ordered against demand. No material hardware order is placed until reservations cover about 70% of a module's sellable GPU-hours, and no site is committed until power, permits and delivery dates are confirmed in signed agreements.

Delivery is timed to energization. Each module's delivery date is tied to its site's power delivery date, so customers reserve against a date they can plan around.

Rubin Ultra follows. The 2027 generation moves to racks of about 600 kW, the density at which the cooling Liquidata specializes in is the only option. Reservations can be placed for either generation.

Next module

Reserve Capacity on the next Vera Rubin module.