NVIDIA Vera Rubin
The next rack-scale platform. Ask us; we quote it when the facility figures are published.
- 72 GPUs per rack
- HBM4
- Liquid cooled rack
- On request
Configurations
Pick the footprint that fits. Every one is sold on the same contract.
- Rack scaleAsk us
- No commitment is taken until flow, pressure, chemistry and floor loading are published.
- Pathway in placeThe first hall
- 800 VDC pathway, floor loading above 4,000 lb per rack, flow headroom.
- Four 5 MW hallsThe campus
- Designed so the next platform lands without a rebuild.
Specifications
- GPUs
- Rack scale per rack
- GPU memory
- Not yet published, HBM4 per GPU
- NVLink
- Not yet published
- CPUs
- Vera
- System memory
- Not yet published
- Networking
- Not yet published
- Power
- Not yet published
- Cooling
- Liquid cooled rack
- Fabric at Fulmis
- InfiniBand or Spectrum-X Ethernet, sized to the workload
- Software
- Slurm and managed Kubernetes
- Location
- A data centre in the Santiago Metropolitan Region
- Available
- On request, when the facility figures are published
Performance
Per rack, as NVIDIA publishes it.
- Published facility figures
- None yet: flow, pressure, chemistry and floor loading are not public
- Commitment
- None until they are
NVIDIA's published figures. Tensor Core numbers carry sparsity unless the row says dense; H100, H200 and RTX PRO figures are per GPU because NVIDIA publishes no node total. Power figures are the ones we reserve and protect to, with NVIDIA's own where it publishes one.
How we deploy it
Vera Rubin is NVIDIA's next rack-scale platform. Nobody has published its flow, pressure, chemistry or floor loading, so we commit to nothing on it today and we quote it when those figures exist.
The first hall is built so that it is not obsolete when Rubin lands: 800 VDC pathway, floor loading above 4,000 lb per rack, and flow headroom on the liquid loop.
Fulmis places the purchase order, or takes delivery of the fleet you already own. Either way we bring it into Chile, commission it against the vendor baseline and operate it for the term. You reserve the capacity, or your own hardware; the workload and the data stay yours.
Terms
- Term
- Three to five years
- Price
- Fixed for the term, in the term sheet
- Commitment
- Take-or-pay
- Prepayment
- None to 25% at signature
- Smallest block
- One rack
- Start
- On request
Other platforms
| Platform | GPUs | GPU memory | NVLink | Power | Cooling | Smallest block | Available |
|---|---|---|---|---|---|---|---|
| GB300 NVL72Rack scale | 72per rack | 20 TB288 GB per GPU | 130 TB/s1.8 TB/s per GPU | 132 to 140 kW155 kW peak | Liquid | 1 rack, 72 GPUs | Q1 2027 |
| GB200 NVL72Rack scale | 72per rack | 13.4 TB186 GB per GPU | 130 TB/s1.8 TB/s per GPU | 120 to 132 kWper rack | Liquid | 1 rack, 72 GPUs | Q1 2027 |
| HGX B3008-GPU node | 8per node | 2.3 TB288 GB per GPU | 14.4 TB/s1.8 TB/s per GPU | About 14 kWper node | Air or liquid | 1 node, 8 GPUs | December 2026 |
| HGX B2008-GPU node | 8per node | 1.4 TB180 GB per GPU | 14.4 TB/s1.8 TB/s per GPU | About 14.3 kWper node | Air or liquid | 1 node, 8 GPUs | December 2026 |
| HGX H2008-GPU node | 8per node | 1.1 TB141 GB per GPU | 7.2 TB/s900 GB/s per GPU | About 10.2 kWper node | Air | 1 node, 8 GPUs | Q1 2027 |
| HGX H1008-GPU node | 8per node | 640 GB80 GB per GPU | 7.2 TB/s900 GB/s per GPU | About 10.2 kWper node | Air | 1 node, 8 GPUs | Q1 2027 |
| RTX PRO 6000 Blackwell8-GPU node | 8per node | 768 GB96 GB per GPU | PCIe Gen 5no NVLink | 5.4 to 6.7 kWper node | Air | 1 node, 8 GPUs | Q1 2027 |