Oct 1, 2025 14 min read

AMAX RackScale 32 with NVIDIA HGX B300

AMAX RackScale 32 with NVIDIA HGX B300
RackScale 32 with NVIDIA HGX B300
AMAX RackScale 32

Accelerating AI in Every Data Center

High-density, rack-scale solution engineered for large-scale enterprise AI workloads with 32 NVIDIA HGX™ B300 GPUs

AMAX RackScale 32 with NVIDIA HGX B300 for AI workloads
Left Aligned Gradient Text with Divider
Key Features
AMAX Specialized IT Solutions
Tensor/Transformer Cores

Tensor/Transformer Cores

Up to 576 specialized cores that accelerate transformer operations (e.g., attention layers) critical to LLM performance.

High Memory Capacity

High Memory Capacity

Up to 8.4TB of HBM3e memory, enabling efficient handling of massive models and long context windows without bottlenecks.

In-Node Bandwidth

In-Node Bandwidth

NVIDIA NVLink/NVSwitch interconnect keeps GPUs fully utilized across large-scale training workloads.

High-Speed Networking

High-Speed Networking

800Gbps NVIDIA InfiniBand for rapid multi-node synchronization across distributed AI clusters.

Left Aligned Gradient Text with Divider
System Architecture
RackScale Overlay Diagram
800G InfiniBand
Networking
4x 8U Servers
Up to 8.4TB total
HBM3e GPU memory

Fully Configured for AI at Scale

The AMAX RackScale 32 with NVIDIA HGX™ B300 is a fully configured rack solution that combines compute, networking, and storage in one system. Each rack includes 4x 8U compute servers powered by 32 Blackwell Ultra GPUs and dual socket Intel® Xeon® 6700 processors, delivering up to 8.4TB of HBM3e GPU memory.


Built on the NVIDIA reference design, the rack features high-efficiency air cooling, 800Gbps InfiniBand networking, and a high-performance storage appliance. With 576 PFLOPS of FP4 and 288 PFLOPS of FP8 Tensor Core performance, RackScale 32 provides the scalability and reliability needed for next-generation AI workloads.

Left Aligned Gradient Text with Divider
AI Training & Inference Performance
Llama 3.1 405B real time throughput chart

Next Level Training Performance

The second generation Transformer Engine with FP8 enables 4x faster training for large models like Llama 3.1 405B. Combined with NVLink at 1.8 TB/s, InfiniBand networking, and Magnum IO software, it scales efficiently across enterprise clusters.

Llama 3.1 405B model training speedup chart

Real Time Inference

HGX B300 delivers up to 11x higher inference performance over the Hopper generation. Blackwell Tensor Cores with TensorRT LLM innovations accelerate inference for Llama 3.1 405B and other large models.

Left Aligned Gradient Text with Divider
Server Design

AceleMax® AXG-828U

The AceleMax® AXG-828U pairs 8x NVIDIA HGX B300 GPUs with dual Intel Xeon 6700-series CPUs, PCIe Gen 5 NVMe storage, and 12 expansion slots. Designed for dense AI deployments, it delivers high-speed interconnects and efficient thermal control in a 4U rackmount form factor.

Learn More
AceleMax® AXG-828U B300 GPU Server
Left Aligned Gradient Text with Divider
Engineering Expertise
AMAX Specialized IT Solutions
Solution Architect

Solution Architects

AMAX's solution architects optimize IT configurations for performance, scalability, and industry-specific reliability.

Networking Solutions

Networking

AMAX designs custom networking topologies to enhance connectivity and performance in AI and HPC environments.

Thermal Management

Thermal Management

AMAX implements innovative cooling technologies that boost performance and efficiency in dense computing setups.

Benchmarking and Optimization

Compute Optimization

AMAX ensures maximum performance through benchmarking and testing, aligning hardware and software for AI workloads.

Left Aligned Gradient Text with Divider
AI Architects
Design to Deployment

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.

Left Aligned Gradient Text with Divider
HostMax
Networking Text and Image

Activate Your Infrastructure Instantly with HostMax™

HostMax™ is AMAX’s in-house deployment service that lets you power on and operate your liquid-cooled AI systems as soon as they’re built. Instead of waiting for colocation space, HostMax™ provides immediate hosting at AMAX’s facility, enabling a direct transition from assembly to deployment for testing, validation, and early production.

Learn More
hostmax hosting area render
Left Aligned Gradient Text with Divider
Order Now
AMAX RackScale 32 with HGX B300
RackScale 32 Feature

AMAX RackScale 32

AMAX RackScale 32 combines compute performance with efficient scalability for industries including healthcare, finance, public sectors, manufacturing, neoclouds, and research institutions.

  • Dual Socket Intel® Xeon® 6700E/6700P series processors
  • 32x NVIDIA Blackwell Ultra GPUs
  • Up to 8.4TB total HBM3e GPU memory per rack
  • Total FP4 Tensor Core 576 PFLOPS
Left Aligned Gradient Text with Divider
Request a Quote
Form with Responsive Styled Box
Custom Side by Side Boxes with SVG and Buttons
Feature SVG
Speak to an AMAX representative now.
Contact Us
Feature SVG
Don't see the right solution for you here?
Tell us more