Europe
Availability on request
Price on requestConfiguration and region to be confirmed
GLOBALATLAS AI · B200
NVIDIA B200 · 180 GB
This page describes the 180 GB HGX B200 configuration. Other platform variants must be checked against their exact specification.
Blackwell180GB VRAM
- Memory technology
- HBM3e
- Workloads
- Training and inference with high memory demand
Build the server around the Blackwell workload
- 01
180 GB HGX B200 reference variant
- 02
Runtime support and numerical precision
- 03
Host memory and GPU interconnect
Compare B200 with H100 when the working set or topology is changing. Benchmark the same model and precision on both systems.
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
Choosing B200
Which B200 variant is compared here?
The catalog reference is HGX B200 with 180 GB per GPU. Confirm the exact platform and GPU count in a server configuration before comparing prices.
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.