OpenMetal Expands v5 Hardware with NVIDIA Blackwell and H200 GPU Servers

OpenMetal announced in a press release the expansion of its v5 hardware catalog with two private GPU server lines, the RP6000 and H200. The RP6000 is built on the NVIDIA RTX PRO 6000 Blackwell Server Edition, and the H200 is built on the NVIDIA H200 NVL. Both servers are designed for AI, machine learning, and high performance computing workloads.

Each system uses dual Intel Xeon 6530P processors with 1TB of DDR5-6400 memory, expandable to 2TB, PCIe 5.0 connectivity, NVMe storage, and 40Gbps private networking. These specifications align with the rest of OpenMetal’s v5 platform, providing consistent performance across CPU, memory, and I/O subsystems.

The RP6000 supports one or two NVIDIA RTX PRO 6000 Blackwell GPUs per server, each offering 96GB of GDDR7 memory and 24,064 CUDA cores. The H200 supports one or two NVIDIA H200 NVL PCIe GPUs, each with 141GB of HBM3e memory and 4.8 TB/s bandwidth. Every H200 server includes a five-year NVIDIA AI Enterprise software subscription.

Both GPU server lines are delivered as single-tenant bare metal systems with no shared hypervisor. They support frameworks such as PyTorch, TensorFlow, JAX, and Hugging Face Transformers. The RP6000 and H200 servers are available now in OpenMetal’s US East data center in Ashburn, Virginia, with additional locations planned.