AMAX AI at Any Scale
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.
LiquidMax® LX-5b Workstation
The LiquidMax LX-5b is equipped with 4 liquid-cooled GPUs, the system achieves a hybrid floating-point performance up to 5940 TFLOPS, and GPU memory bandwidth exceeds 2000 GB/s. Parallel CPU and GPU, for more convenient maintenance.
- Fully enclosed liquid cooling design
- Supports up to 4 liquid-cooled GPUs
- Full liquid cooling for both CPU and GPU
- Operates at full load wtih only 50dB noise at 30°C ambient temperature
AMAX RackScale 32 with NVIDIA HGX B300
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
AMAX RackScale 32 with NVIDIA RTX PRO 6000 Blackwell Server Edition
AMAX RackScale 32 with NVIDIA RTX PRO 6000 Blackwell Server Edition delivers a rack-scale platform designed for inference at scale, agent based systems, and advanced 3D computing.
- Dual Socket AMD EPYC 9005 Series Processors
- 32x NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs
- Up to 3 TB of ECC GDDR7 memory per rack
- Total FP4 Tensor Core 128 PFLOPS
LiquidMax® RackScale 64
The LiquidMax® RackScale 64 is a high-density, fully liquid-cooled 44U rack solution designed to support advanced AI training and inference.
- Supports up to 64x NVIDIA Blackwell GPUs
- 8x 4U liquid-cooled servers with NVIDIA NVLink interconnect
- Integrated CDU and vertical cooling distribution manifold
- Rack-scale solution with pre-integrated compute, cooling, and power
- NVIDIA Quantum-2 400G InfiniBand or Spectrum-4 400GbE for compute and storage
LiquidMax® RackScale 128
The LiquidMax® RackScale 128 is a fully integrated rack-scale design, engineered for high-density AI deployments with advanced cooling and power efficiency.
- Supports up to 128x NVIDIA Blackwell GPUs or AMD Instinctâ„¢ MI355X / MI325X accelerators
- Liquid-to-liquid cold plate cooling with CDU support
- Open rack architecture 51OU rack with centralized 48V busbar power
- Integrated leak detection and system monitoring
LiquidMax® RackScale 72
NVIDIA GB300 NVL72 with 36 Grace™ Arm® Neoverse V2 CPUs and 72 Blackwell Ultra GPUs
- 72 NVIDIA B300 GPUs and 36 Grace CPUs per rack
- Fully Liquid-cooled
- 288GB HBM3e per GPU
- 800Gb/s NVIDIA Quantum-2 InfiniBand or Spectrum-X Ethernet