NVIDIA® DGX Station™ A100 «NEW»
NEWThe NVIDIA<sup>®</sup> DGX Station™ A100 brings powerful updates to the popular DGX Station while retaining the plug and play, workstation form factor. The DGX Station has been popular with AI teams for its ability to deliver serious AI processing power without the need for data centre power and cooling. The new DGX Station A100 has upgraded capabilities and new flexibility that will make this the go-to solution for AI workgroups.
- 4 x A100 Tensor Core GPU’s with either 40GB or 80GB memory each
- Multi-Instance GPU function, allows the 4 x A100’s to be split or combined across a potential 28 individual GPU instances
- 2.5 petaFlOPS of performance that can be used without limits – across data analytics, training and inference workloads
- Fully optimised AI software stack.
The DGX Station delivers data centre performance without the data centre overheads!
Download the DGX Station A100 datasheet for full specifications.
Get a Quote
GPUs
4 x NVIDIA A100 80GB Tensor Core GPUs, or 4 x NVIIDA A100 40GB Tensor Core GPUs
Performance
2.5 petaFLOPS AI, 5 petaOPS INT8
CPU
Single AMD 7742, 64 Cores, 2.25GHz (base) - 3.4GHz (max boost)
System Memory
512GB DDR4
Storage
OS: 1 x 1.92TB NVME | Internal Storage: 7.68TB U.2 NVME
Networking
Dual-port 10Gbase-T Ethernet LAN, Single-port 1Gbase-T Ethernet, BMC management port
DGX Display Adapter
4GB GPU memory, 4 x Mini DisplayPort
System Power Usage
1.5 kW at 100-120 Vac
System Weight
43.1 kg | Packed weight 57.93 kg
System Dimensions
H: 639mm x W: 256mm x L: 518mm
Operating Temperature
5º to 35º C