NVIDIA HGX H200 combines multiple H200 Tensor Core GPUs with a high-speed
interconnect powered by NVIDIA NVLink® and NVSwitch™ to enable the creation of the
world’s most powerful scale-up servers while Cirrascale delivers it all to you via the cloud.

NVIDIA HGX H200: The World’s Leading AI Computing Platform is Coming Soon to the Cirrascale AI Innovation Cloud

As workloads explode in complexity, there’s a need for multiple GPUs to work together with extremely fast communication between them. NVIDIA HGX H200 combines multiple H200 GPUs with a high-speed interconnect powered by NVIDIA NVLink and NVSwitch™ to enable the creation of the world’s most powerful scale-up servers.

HGX H200 is available as a server building block in the form of integrated baseboards in eight or four H200 GPU configurations. The eight-GPU configuration offers full GPU-to-GPU bandwidth through NVIDIA NVSwitch. Leveraging the power of H200 multi-precision Tensor Cores, an eight-way HGX H200 provides over 32 petaFLOPS of FP8 deep learning compute and over 1.1TB of aggregate HBM memory for the highest performance in generative AI and HPC applications.

HGX H200 enables standardized servers that provide the highest performance on various application workloads, including LLM training and inference for the largest models beyond 175 billion parameters, while accelerating time to market for NVIDIA’s ecosystem of partner server makers.

Be sure to sign-up today so that our account managers can notify you the moment HGX H200 becomes available in our AI Innovation Cloud.

Be the First in Line!

Sign-up to access the NVIDIA HGX H200 platform as soon as it becomes available on the Cirrascale AI Innovation platform.


Data Sheet

Download the HGX H200 Cloud Service data sheet to learn more about our offering.


NVIDIA HGX H200 in the Cloud with Cirrascale Cloud Services

We offer fully-managed NVIDIA GPU-based clusters at a fraction of the cost of traditional cloud service providers. These bare-metal servers are completely dedicated to you with no contention and no performance issues due to virtualization overhead.

Our flat-rate, no surprises billing model means we can provide you with a price that is up to 30% lower than the other cloud service providers. We also don't nickel-and-dime you by charging to get your data in to or out of our cloud. Instead, we charge no ingress or egress fees so you never receive a supplemental bill.


Sign Up for an NVIDIA HGX Instance

Sign-up to get added to our waiting list so you'll be one of the first on the NVIDIA HGX H200.