GH100 Hopper
14,592
456 (4th Gen)
94 GB HBM3
3.9 TB/s
PCIe 5.0 x16
350W
600 GB/s dual-GPU
IN STOCK
LLM inference serving, large model deployment, dual-GPU NVLink workloads, enterprise AI
Need H100 NVL for your LLM inference cluster? Get a quote.
Contact us for volume pricing, lead times, and configuration options.
Request Quote