Europe
Availability on request
Price on requestConfiguration and region to be confirmed
GLOBALATLAS AI · GH200 96 GB
NVIDIA GH200 96 GB · 96 GB
GH200 combines an Arm Grace CPU with a Hopper GPU. This variant has 96 GB HBM3 GPU memory; CPU-attached LPDDR5X is separate.
Grace Hopper96GB VRAM
- Hardware variant
- Grace CPU + Hopper GPU, 96 GB GPU memory
- Memory technology
- HBM3
- Workloads
- Arm-based AI and coherent CPU/GPU workloads
Configuring GH200 96 GB
- 01
Use Arm64-compatible containers and dependencies
- 02
Distinguish 96 GB GPU memory from CPU memory
- 03
Specify one Superchip or a separate NVL2 configuration
Regional configurations
USA
Availability on request
Price on requestConfiguration and region to be confirmed
Asia
Availability on request
Price on requestConfiguration and region to be confirmed
Technical references
Specification 1 →YOUR CONFIGURATION
Request an infrastructure quote
Choose resources and operating time. We will confirm a price for your configuration.
Each resource has its own listed configuration. Multiple GPU servers do not form an NVLink cluster. Monthly rates cover the full billing period; storage and traffic outside the configuration are not included.