NVIDIA VR200 NVL72
NVIDIA's Vera Rubin NVL72 rack is on a waitlist for first allocation, and we design the site before the racks arrive.
- GPUs
- 72 × Rubin
- GPU memory
- 20.7 TB HBM4 per rack
- NVLink
- 260 TB/s across 72 GPUs
- Rack power
- Not published
- Status
- Waitlist
NVIDIA VR200 NVL72 specifications.
The published figures, and the ones a site plan still waits on.
- Generation
- Rubin
- GPUs
- 72 GPUs per rackEvery GPU in the rack shares one NVLink domain. The scale-out network only joins racks to each other.
- CPUs
- 36 Vera per rackVera in place of Grace, one CPU for every two GPUs.
- GPU memory
- 288 GB HBM4 per GPU, 20.7 TB per rackThe same capacity as GB300 NVL72. The step is from HBM3e to HBM4.
- NVLink
- 260 TB/s across 72 GPUs3.6 TB/s per GPU, against 1.8 TB/s per GPU on GB300 NVL72.
- Scale-out network
- Confirmed with the orderWe confirm the NIC with the order. GB300 NVL72 runs 800 Gb/s per GPU, and we plan cabling for at least that.
- Cooling
- Liquid, at the rackAs on GB300 NVL72, every position needs facility water. The supply temperature is set in the design.
- Rack power
- Not publishedGB300 NVL72 draws up to 142 kW per rack. Until NVIDIA gives a figure, we plan above that.
- Rack weight
- Confirmed with the orderA loaded GB300 NVL72 rack is about 1.4 to 1.6 metric tons. The floor is planned for at least that.
- Availability
- Waitlist for first allocationThere's no lead time yet; the proposal sets one.
VR200 NVL72 figures are from NVIDIA's Vera Rubin NVL72 page. Where a figure isn't set yet, the note gives the GB300 NVL72 figure we plan from.
What to have in the hall before allocation.
One liquid-cooled rack in front elevation. NVIDIA hasn't published a rack power figure for VR200 NVL72, and network and weight are confirmed with the order. Each note says what we plan around until then.
- 1
Power sized above GB300 NVL72
GB300 NVL72 draws up to 142 kW per rack. With no published figure for VR200 NVL72, we size feeds, busway and transformers above that and check the design against the order.
- 2
Facility water at every position
Like GB300 NVL72, the rack is cooled by liquid, so each position needs facility water and coolant distribution. We set the supply temperature in the design, against NVIDIA's figures for the order.
- 3
Cable paths with room to spare
The NIC and the fabric are confirmed with the order. Until then, cable paths and leaf positions are sized for at least 800 Gb/s per GPU, the GB300 NVL72 figure.
- 4
A floor rated for a full rack
A GB300 NVL72 rack weighs about 1.4 to 1.6 metric tons loaded, so we rate the floor for at least that and confirm it against the shipping weight.
Vera Rubin NVL72 next to GB300 NVL72.
Both are 72-GPU liquid-cooled racks, a generation apart. VR200 NVL72 brings Vera CPUs, HBM4 and twice the NVLink bandwidth; GB300 NVL72 can be built now.
| GB300 NVL72 | VR200 NVL72 | |
|---|---|---|
| Generation | Blackwell Ultra | Rubin |
| CPUs | 36 Grace per rack | 36 Vera per rack |
| GPU memory | 288 GB HBM3e per GPU | 288 GB HBM4 per GPU |
| NVLink | 130 TB/s across 72 GPUs | 260 TB/s across 72 GPUs |
| Scale-out network | 800 Gb/s per GPU (ConnectX-8) | Confirmed with the order |
| Rack power | Up to 142 kW per rack | Not published |
| Rack weight | About 1.4 to 1.6 metric tons | Confirmed with the order |
| Availability | Dates set in the proposal | Waitlist for first allocation |
Both are quoted per project. A hall built with headroom can take GB300 NVL72 racks now and VR200 NVL72 racks once allocation arrives.
Other NVIDIA platforms we build on.
The same four stages on each: design, source, build and operate. All hardware.
- NVIDIA HGX B300Blackwell Ultra8 GPUs per node288 GB HBM3e per GPUAirAvailable
- NVIDIA HGX B200Blackwell8 GPUs per node180 GB HBM3e per GPUAirAvailable
- NVIDIA GB200 NVL72Blackwell72 GPUs per rack186 GB HBM3e per GPULiquidAvailable
- NVIDIA GB300 NVL72Blackwell Ultra72 GPUs per rack288 GB HBM3e per GPULiquidAvailable
- NVIDIA HGX Rubin NVL8Rubin8 GPUs per node288 GB HBM4 per GPULiquidWaitlist
VR200 NVL72 questions.
We build VR200 NVL72 clusters as a deployment your team runs, a managed cluster you own and we operate, or a reserved cluster we own. Other platforms.
First allocation runs through a waitlist, and we don't publish dates. Yours are written into the proposal when the allocation comes through.
NVIDIA hasn't published a rack figure, and estimates elsewhere don't agree. We size the electrical plant above GB300 NVL72, which draws up to 142 kW per rack, and confirm the design against NVIDIA's figure in the order.
Yes. VR200 NVL72 is another name for NVIDIA's Vera Rubin NVL72: 72 Rubin GPUs and 36 Vera CPUs in one rack.
Yes, at the rack. Every position needs facility water and coolant distribution, so a room cooled only by air has to be retrofitted first.
There's no confirmed figure yet. We rate the floor for a loaded GB300 NVL72 rack, about 1.4 to 1.6 metric tons, as a minimum and check it against the shipping weight.
As a spine-leaf RoCE v2 Ethernet fabric, designed to NVIDIA's reference architecture once the order sets the NIC. The cable paths we lay out before then leave room for at least GB300 NVL72's 800 Gb/s per GPU.
Yes. Power, water, network paths and floor loading are designed with headroom now, then checked against NVIDIA's figures when the order is placed.
On a reserved cluster, the contract has a rollover option. Part of the commitment can move into a newer GPU generation when it ships. On a cluster you own, we plan the site with headroom for VR200 NVL72 racks.