NVIDIA A30 Tensor Core GPU is the most versatile mainstream compute GPU for AI inference and mainstream enterprise workloads. Powered by NVIDIA Ampere architecture Tensor Core technology, it supports a broad range of math precisions, providing a single accelerator to speed up every workload. Built for AI inference at scale, the same compute resource can rapidly re-train AI models with TF32, as well as accelerate high-performance computing (HPC) applications using FP64 Tensor Cores. Multi-Instance GPU (MIG) and FP64 Tensor Cores combine with fast 933 gigabytes per second (GB/s) of memory bandwidth in a low 165W power envelope, all running on a PCIe card optimal for mainstream servers.
Graphics Engine | A30 (Ampere) |
Bus Standard | PCI Express 4.0 |
CUDA Cores | 3804 |
Peak double precision floating point performance | 5.2 Tflops |
Peak single precision floating point performance | 10.3 Tflops |
Peak half precision | 165 Tflops |
Video Memory | 24GB HBM2 with ECC |
Memory Interface | 3072-bit |
Memory Bandwidth | 0,933 TB/s |
NVLink Technology | N/A |
Power Consumption | 165 W |
Power Connectors | 1 x 8-pin |
Dimensions | 111mm x 267mm x 40mm |
Why not Tell A Friend about this product, all you need to do is fill out their information below and click send.
Get your order delivered the next working day for £5.99, available when ordering Monday - Thursday and before 17:00 on that day if the product is in stock and your payment has cleared.
Get your order delivered the next working day before 12:00pm for £10.98, available when ordering Monday - Thursday and before 17:00 on that day if the product is in stock and your payment has cleared. Some orders if via PayPal and the first customer order may not clear in time.
If you need your order at the weekend, for £12.58, you can specify the day you wish to have it delivered to you, Saturday or Sunday providing your order has been placed by 17:00 on the Friday before.
Economy delivery is available on all orders of any value being shipped within the UK.