NVIDIA DGX A100 640GB
Eight A100 80GB GPUs with 640GB HBM2e and MIG partitioning across the node.
We help you choose, configure, and deliver the right system — no obligation.
Configuration at a Glance
Tailored per engagement. Full technical overview below.
Configuration Options
Core specifications for this system. Every component is configurable to your workload — request a quote for a tailored build.
8× NVIDIA A100 80GB SXM4
Dual AMD EPYC 7742, 128 cores total
640GB HBM2e total
Overview
DGX A100 is the Ampere-generation NVIDIA system, with eight A100 80GB SXM4 GPUs, 640GB of HBM2e and dual AMD EPYC processors. Its distinguishing feature is Multi-Instance GPU: each A100 partitions into as many as seven hardware-isolated instances, which makes a single node an unusually good platform for serving many small models or giving separate teams guaranteed capacity on shared hardware.
Who This Solution Is For
Business Benefits
MIG partitioning
Up to seven hardware-isolated instances per GPU — 56 across the node — with guaranteed memory and compute.
Matches an installed base
Adds capacity to existing A100 clusters without mixing GPU generations mid-job.
Multi-tenant by design
Hardware isolation makes shared research and departmental platforms straightforward to run.
Established economics
A mature platform where the cost per usable FLOP is frequently the deciding factor.
Typical Business Use Cases
Multi-tenant inference serving across many small models
Shared university and departmental research clusters
Extending an existing DGX A100 deployment
HPC and simulation workloads tuned to Ampere
Industry Applications
Technical Overview
A 6U system with eight A100 80GB SXM4 GPUs on an NVLink baseboard with NVSwitch, dual AMD EPYC 7742 processors, 2TB system memory, and ConnectX adapters for 200Gb/s InfiniBand. Storage capacity is configurable and confirmed at quotation.
| GPU / Accelerator | 8× NVIDIA A100 80GB SXM4 |
| GPU Memory | 640GB HBM2e total |
| GPU Interconnect | NVLink with NVSwitch, 600GB/s GPU-to-GPU |
| CPU | Dual AMD EPYC 7742, 128 cores total |
| System Memory | 2TB |
| Partitioning | MIG — up to 7 isolated instances per GPU |
| Networking | ConnectX 200Gb/s InfiniBand |
| Form Factor | 6U rackmount |
Specifications are indicative and configured to each engagement. Request a quote for a configuration tailored to your requirements.
Warranty, Support & Fulfillment
Every system ships from an authorized channel, configured and tested, with the documentation enterprise buyers need — backed by warranty and a dedicated account team.
Enterprise Warranty
Full manufacturer warranty with optional on-site, next-business-day support and extended coverage.
Authorized Channel
Sourced through Tier-1 distribution and OEM partners — never grey market. Asset & warranty records included.
Lead Time & Deployment
48-hour quotes, then configured, burn-in tested, and delivered on a committed schedule.
Nationwide Fulfillment
Coordinated logistics, rack-and-stack, and delivery wherever your infrastructure lives.
Frequently Asked Questions
What does MIG actually give me?
Multi-Instance GPU splits each A100 into as many as seven hardware-isolated instances, each with its own memory and compute slice. That matters if you are serving many small models, or giving separate teams guaranteed capacity on shared hardware without them contending. It does not matter if you run one large job across whole GPUs, and it is not a reason on its own to choose Ampere over a later generation.
How is DGX quoted and delivered?
As a configured system rather than a boxed part. We confirm the exact platform revision, the networking and storage around it, rack power and cooling requirements, and the support term, then issue an itemised quote. Current availability and lead time are stated on that quote — accelerator allocation moves, and any figure published on a web page would be wrong for most buyers by the time they read it.
Should I buy DGX or an HGX system from Dell, Supermicro or HPE?
The GPUs and the NVLink fabric are the same silicon either way. DGX gives you one vendor accountable for the whole stack including the software environment, and is the designed unit if you are heading toward SuperPOD. An HGX system from a server vendor gives you your existing management tooling, support relationship and configuration choices. If your operations are already standardised on Dell or HPE, that consistency is frequently worth more than it looks on a spreadsheet. We supply both and will tell you which fits.
Can you supply the networking and storage as well?
Yes, and these should be quoted together. A DGX node without its InfiniBand fabric, parallel storage and rack power is not a working cluster. We specify the switches, cables, optics and layout alongside the systems.
Hardware Assistance
Configure the NVIDIA DGX A100 640GB with Nexus Compute
Tell us your requirements and a hardware specialist will help you specify, configure, and quote the right system — typically within two business days. No obligation.