NTS Liquid Cooling Racks
Liquid-Cooled Rack & CDU-Ready Platforms
Rack-level DLC hardware—manifolds, busbars, and CDU handoff points for AI factory rows.
Liquid Cooling Racks
CDU-ready row hardware
Engineer-to-order NTS Liquid Cooling Racks — configure below or request an architect-validated BOM; procurement via SEWP V, ITES-4H, and SLED vehicles.
Architects validate thermals, fabric, and imaging baselines in Fremont before freight—one integrator remains accountable through handoff.
Use the paths below to continue into related catalogs, or request an architecture review on your vehicle.
NTS documents rack elevation, PDU draw, thermal headroom, and driver baselines on every RFQ so facility teams are not discovering constraints at install.
Related storage, networking, and software lines can ride the same quote when your vehicle and SOW allow—keeping multi-vendor programs under one accountable integrator.
Liquid racks
Liquid-cooling rack platforms
Configure Advance Liquid Cooling SKUs or request an architecture review.
- Engineer-to-order
- Burn-in included
- Contract quoting
- Engineer-to-order
- Burn-in included
- Contract quoting
NTS catalog
Available Advance Liquid Cooling configurations
Select a platform below to configure, request a quote, or add to your procurement package.
- Configure & quote
- CPU / memory / storage specs
- Contract-ready procurement
Configure & quote
CPU / memory / storage specs
Contract-ready procurementDisplay per page
Supermicro NVIDIA GB200 NVL72
Rack-scale solution with NVIDIA GB200 Grace™ Blackwell Superchip providing 72 NVIDIA B200 GPUs and 36 Grace CPUs per rack
Direct Liquid-Cooling for up to 40% reduction in electricity cost for the data center
Comprehensive Service from consultation to full-scale deployment, providing all necessary parts, networking solutions, and onsite installation services
Advanced Networking Ready supporting NVIDIA Quantum-2 InfiniBand or Spectrum-X Ethernet
NTS Elite Fusion Grace Blackwell Ultra AI POD | NVIDIA Liquid-Cooled AI Platform
- Latest NVIDIA GB300 Grace™ Blackwell Ultra Superchips
- Liquid-cooled, rack-scale solution that boasts 36 NVIDIA GraceTM CPUs and 72 NVIDIA Blackwell Ultra GPUs.
- Features a liquid cooling system that reduces energy consumption
- NVIDIA® NVLink™ technology within single domain.
NTS Elite Fusion Grace Blackwell AI POD | NVIDIA GB200 Liquid-Cooled
- Full rack with 72 NVIDIA Blackwell GPUs
- 36 NVIDIA Grace CPUs and 5th-gen NVIDIA NVLink
- Supports liquid cooling and scale-up ecosystem-ready.
- Enabling trillion-parameter LLM inference and training
Specifications shown are reference configurations—final BOM validated by NTS architects for your workload, facility power, and security baseline.
Frequently asked questions
Nodes, manifolds/CDU interfaces, power, and cable plans - validated as a thermal system, not loose servers.
- Elevation drawings
- Facility coordination
Often 30 kW+ for dense AI; exact numbers follow GPU mix and CDU capacity. NTS supplies worksheets early.
- Floor loading matters
- No surprise heat loads
Prefer aligned hardware + integration CLINs so acceptance covers the rack, not orphan nodes.
- Vehicle-dependent
- Ask at RFQ
Leak checks, flow verification, thermal soak, and GPU/fabric tests at representative load - documented for audit.
- Fremont staging first
- On-site options
