Solution Overview
The LiquidMax® RackScale 128 is a fully liquid-cooled 51OU AI rack built on the OCP ORv3 standard. Designed for hyperscale deployments, it delivers the GPU density, thermal efficiency, and power infrastructure required to support large-scale AI and ML workloads.
Key Features
- Supports up to 128x NVIDIA® Blackwell B200 GPUs or AMD Instinct™ MI300X / MI325X accelerators
- 8x OCP ORv3 5OU compute trays with cold plate liquid cooling
- Centralized 48V busbar power distribution for improved efficiency
- Built-in leakage detection, CDU support, and optional RDHx integration
- Supports dual 400W CPUs and high-performance DDR5 memory
- PCIe Gen 5 expansion for high-speed networking and connectivity
System Overview
| Component | Details |
|---|---|
| GPU | 128x GPUs (8x 5OU compute trays) |
| Cooling | Liquid-to-liquid cooling with CDU support and active leakage detection |
| Architecture | OCP ORv3 51OU rack with 8x 5OU trays |
| Power | 8x 33kW shelves, centralized 48V busbar distribution |
| Management | Integrated leakage detection trays and monitoring |
Compute Node Specifications
| Component | Details |
|---|---|
| CPU | 2x AMD Turin 9655, 96-core, SP5 (2-socket), up to 400W TDP |
| Memory | 24x DDR5 DIMM slots, 96GB RDIMM (5600MT/s), 1DPC |
| Expansion Slots | 6x PCIe 5.0 x16 (SS FHHL): - 5x 400Gb/s single-port ConnectX-7 or BCM957608-P1400GQF00 adapters - 1x Dual-port 10Gb NIC |
Built for Hyperscale AI
The RackScale 128 is designed for large-scale cloud providers, data centers, and enterprises with extreme compute requirements. The OCP ORv3 platform supports wider 21" racks for improved airflow and accessibility, while front-to-back cooling and blind-mate manifolds simplify installation and maintenance.
Its cold plate liquid cooling ensures stable operation under sustained load. The 48V power busbar architecture improves electrical efficiency, minimizes cabling, and enhances serviceability.
OCP ORv3 Advantages
- Modular 5OU tray design for scalable deployment
- Front-access compute and power nodes
- Shared busbar reduces complexity
- Blind-mate liquid manifolds for efficient maintenance
- 21” chassis format increases airflow compared to traditional 19” racks
Why AMAX
AMAX helps organizations deploy advanced computing infrastructure with confidence. From thermal and mechanical engineering to rack integration, testing, and deployment support, our team delivers reliable, high-performance solutions built for AI and high-density workloads.
With over 40 years of experience, AMAX engineers transform standard components into fully integrated solutions optimized for thermal, electrical, and mechanical performance.
Learn how AMAX can help you deploy high-density AI infrastructure with efficiency, reliability, and scalability.