What we are building
HGX B200 and B300 nodes in a Santiago data centre, live from December 2026. A first hall of 864 Blackwell Ultra GPUs in an existing Santiago data centre, live Q1 2027, built against one signed contract and looking for its offtaker. Then a permitted 20 MW campus.
Ready first
Blackwell nodes, live from December 2026
NVIDIA HGX B200 and HGX B300, eight GPUs per node, air cooled, in a Santiago data centre. From one node up, joined by InfiniBand into one cluster when you take more than one. Reserve now for a December 2026 start, while the GB300 hall follows in Q1 2027.
NVIDIA HGX B300
8 Blackwell Ultra GPUs, 2.3 TB HBM3e per node, ConnectX-8 at 800 Gb/s per GPU. Training and inference.
NVIDIA HGX B200
8 Blackwell GPUs, 1.4 TB HBM3e per node, ConnectX-7 at 400 Gb/s per GPU. Training and inference.
- Live from
- December 2026
- Smallest block
- One node, 8 GPUs
- Cooling
- Air cooled
- GPU fabric
- InfiniBand, sized to the cluster
- Software
- Slurm and managed Kubernetes
- Location
- A data centre in the Santiago Metropolitan Region
The first hall
864 GPUs, one training cluster
Twelve NVIDIA GB300 NVL72 racks in an existing data centre in the Santiago Metropolitan Region, joined by an InfiniBand Quantum-X800 fabric. One rack is the smallest block and twelve is the whole hall.
- GPUs
- 864 Blackwell Ultra
- Platform
- 12 × NVIDIA GB300 NVL72
- GPU fabric
- InfiniBand, Quantum-X800, rail optimised
- Built for
- Training
- Rack power
- 132 to 140 kW rated, 155 kW peak
- Cooling
- Liquid cooled racks
- Software
- Slurm and managed Kubernetes
- Storage
- Parallel file system, sized to the workload
- Smallest block
- One rack, 72 GPUs
- Location
- An existing data centre in the Santiago Metropolitan Region
- Electrical supply
- 380 to 400 V at 50 Hz, specified from the first drawing
- First rack live
- Q1 2027
What comes next
The campus: 20 MW
A permitted greenfield site in the Santiago Metropolitan Region, planned as four 5 MW halls. Every permit the 20 MW campus needs is held, including the building permit. The builder and the site are named under a mutual NDA.
- 20 MW IT
- 25 to 27 MW at the meter
- 8,640 GPUs
- 120 racks in four halls
- 18 months
- To all four halls energized, per the contractor
Built to Chile
The supply
380 to 400 V at 50 Hz. NVIDIA reference designs assume 415 or 480 V at 60 Hz, so the power shelves are specified to the Chilean supply from the first drawing.
The ground
Slabs anchored for seismic load, to the standard in force.
The water
Dry heat rejection. No water is consumed in cooling.
The next platform
800 VDC pathway, floor loading above 4,000 lb per rack and flow headroom, so the hall is not obsolete when Vera Rubin lands.