Unparalleled Density
Fully liquid-cooled OCP ORv3 rack supporting up to 128 GPUs, purpose-built for hyperscale AI infrastructure.
128x GPU Support
Supports up to 128x NVIDIA® Blackwell B200 GPUs or AMD Instinct™ MI300X / MI325X accelerators in a single OCP ORv3 rack.
Enhanced Cooling Capacity
Advanced liquid cooling technology expands the range of applications and enhances performance reliability.
Streamlined Servicing
Designed for hassle-free maintenance with no facility modifications required and easy front-side, blind mate connections.
Reduced Power Usage
Maximizes energy efficiency by outperforming air-cooling methods, significantly reducing power consumption.
System & Tray
Engineered for Scalable AI
The LiquidMax® RackScale 128 features a modular 51OU OCP ORv3 design with 8× 5OU compute trays, supporting up to 128 GPUs. Cold plate liquid cooling with CDU support and active leak detection ensures thermal stability, while centralized 48V busbar power and integrated monitoring streamline data center deployment and management.
Engineering Expertise
Our team of thermal, electrical, mechanical, and networking engineers are skilled in designing solutions designed to your specific requirements.
Solution Architects
AMAX's solution architects optimize IT configurations for performance, scalability, and industry-specific reliability.
Networking
AMAX designs custom networking topologies to enhance connectivity and performance in AI and HPC environments.
Thermal Management
AMAX implements innovative cooling technologies that boost performance and efficiency in dense computing setups.
Compute Optimization
AMAX ensures maximum performance through benchmarking and testing, aligning hardware and software for AI workloads.
Built to Maximize Every Unit
Each 5OU node in the RackScale 128 is a modular assembly of two 2OU GPU trays and a 1OU compute tray. These trays combine dual AMD CPUs, high-speed DDR5 memory, and PCIe Gen 5 expansion, delivering the balanced compute, memory, and networking foundation needed to power demanding AI workloads at scale.
Open Rack Architecture
- 21-Inch Open Rack V3: 29% additional front surface area, optimizing server component airflow.
- High Voltage DC Busbar: Removes the need for rack PDUs, outlets, and power cords at the rear of the rack.
- Liquid Cooling Solutions: Enhances efficiency, density, and sustainability through direct-to-chip cooling methods.
- High Density Power Shelf: 48V DC power directly to the busbar, eliminating traditional power supplies.
- Rear-Mounted Liquid Manifold: Facilitates blind-mate connection for easy installation and maintenance.
- Open Rack V3 High Density System: Improves power savings and operational efficiency.
From Design to Deployment
AMAX's approach to AI solutions begins with intelligent design, emphasizing the creation of high-performance computing and network infrastructures tailored to AI applications. We guide each project from concept to deployment, ensuring systems are optimized for both efficiency and future scalability.
LiquidMax® RackScale 128
The LiquidMax® RackScale 128 is a fully integrated OCP ORv3 system, engineered for high-density AI deployments with advanced cooling and power efficiency.
- Supports up to 128x NVIDIA® Blackwell B200 GPUs or AMD Instinct™ MI300X / MI325X accelerators
- Liquid-to-liquid cold plate cooling with CDU support
- OCP ORv3 51OU rack with centralized 48V busbar power
- Integrated leak detection and system monitoring