What we are building
HGX B200 and B300 nodes, available from December 2026 in Santiago and January 2027 in the United States, on contract. A first hall of 864 Blackwell Ultra GPUs in an existing Santiago data centre, planned for Q1 2027, built against one signed contract and looking for its offtaker. Then a permitted 20 MW campus. Nothing on this page is running yet.
Ready first
Blackwell nodes, available from December 2026
NVIDIA HGX B200 and HGX B300, eight GPUs per node, air cooled. Available from December 2026 in Santiago and January 2027 in the United States, on a signed contract. From one node up, joined by InfiniBand into one cluster when you take more than one.
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.
- Available from
- December 2026 in Santiago, January 2027 in the United States, on contract
- 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, or a colocation facility in the United States
Planned: 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
- Q1 2027, on contract
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.