Product image for illustration; configuration may differ.
NVIDIA H200 NVL
PCIe version of the H200 with 141 GB HBM3e for air-cooled enterprise servers — priced on quote.
| Form factor | PCIe, dual slot |
|---|---|
| GPU memory | 141 GB HBM3e |
| Architecture | NVIDIA Hopper |
| Cooling | Passive (server airflow) |
NVIDIA H200 NVL is built to order and priced per project (configuration, delivery, installation and support).
Check a model against our machines before you buy.
Pick the model and quantisation you plan to run. We'll show whether it fits in memory, how much room is left for context, and the throughput to expect. Estimates come from memory bandwidth and are replaced by our own bench figures where we have them.
Machine
Quantisation
Comfortable. 70 GB spare — room for 128k context, a second small model, or a RAG index in memory. Expect roughly 3.8 tok/s single-stream.
Machines that run this configuration
Weights 42.8 GB at 4.85 bits/param · KV cache 5.0 GB at 16k (fp16, approximate) · 10 GB reserved for OS and runtime. Speed is single-stream decode, memory-bound; prompt processing and batching behave differently. Or WhatsApp an engineer on +44 7515 356 146.
The H200 NVL brings 141 GB of HBM3e to standard air-cooled PCIe servers. NVLink bridges link GPUs together for larger models.
Fitted in a Workstation server or supplied standalone. Before it ships we check it against your chassis (power, airflow, risers, slot layout and NVIDIA-Certified status), burn-in test it and install drivers, CUDA, vGPU and NVIDIA AI Enterprise licensing where needed. Warranty claims and advance replacements are handled by us. Support comes from our own UK engineers, and Trade members get free tech support on every order.
Priced on quote: tell us what you need and we will confirm price, availability and lead time.