NVIDIA A40 Tensor Core GPU
The new NVIDIA® A40 Tensor Core GPU with the new NVIDIA Ampere Architecture delivers increased performance and flexibility for a range of AI and HPC workloads. The NVIDIA A40 is ideal for visualisation, design, creative work, scientific challenges across data analytics, HPC and AI. The NVIDIA A40 is fast and ready for virtualisation – allowing for the power of the NVIDIA A40 to be shared from the Workstation or Server. All components of the A40 have been optimised for speed and processing power – from the PCIe Gen4, to new generation RT and Tensor cores, to faster NVLink® to combine and amplify the power of the NVIDIA A40.
XENON is delivering bespoke solutions based on the PCIe Gen4 with the NVIDIA A40, in servers and workstations across the XENON NITRO Workstation family, and the XENON RADON Intel Servers, and XENON KRYPTON AMD Servers.
Get a QuoteGPU Memory
48 GB GDDR6 with error-correcting code (ECC)
GPU Memory Bandwidth
696 GB/s
Interconnect
NVIDIA NVLink® 112.5 GB/s (bidirectional) PCIe Gen4 16 GB/s
NVLink
2-way low profile (2-slot)
Display Ports
- 3x DisplayPort 1.4*
- A40 is configured for virtualisation by default with physical display connectors disabled. The display outputs can be enabled via management software tools
Max Power Consumption
300 W
Form Factor
4.4" (H) x 10.5" (L) Dual Slot
Thermal
Passive
vGPU Software Support
NVIDIA GRID®, NVIDIA Quadro® Virtual Data Center Workstation, NVIDIA Virtual Compute Server
vGPU Profiles Supported
1 GB, 2 GB, 3 GB, 4 GB, 6 GB, 8 GB, 12 GB, 16 GB, 24 GB, 48 GB
NVENC | NVDEC
1x | 2x (includes AV1 decode)
Secure and Measured Boot with Hardware Root of Trust
CEC 1712
NEBS Ready
Level 3
Power Connector
8-pin CPU