Product image for illustration; configuration may differ.
NVIDIA HGX platform
NVLink-connected multi-GPU baseboards built into partner servers for AI and HPC — priced on quote.
| Type | Multi-GPU server platform |
|---|---|
| Generations | Hopper and Blackwell |
| GPU interconnect | NVIDIA NVLink |
| Built by | NVIDIA-Certified partner servers |
NVIDIA HGX platform 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.
HGX combines NVIDIA GPUs, NVLink, NVIDIA networking and an optimised AI and HPC software stack on one baseboard that server makers build their flagship GPU servers around. We specify the HGX generation and the server around it; ready-configured HGX B200 and B300 servers are also listed.
Workstation runs this as a project: site survey, power and cooling design, rack layout, installation and cabling, then onboarding onto Base Command Manager or Mission Control, Kubernetes or Slurm. Ongoing monitoring and managed support contracts are available. 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.