NVIDIA A40
The NVIDIA A40 is a data center GPU based on the Ampere architecture, combining professional graphics rendering with AI computing power. It features 48GB GDDR6 ECC memory, second-generation RT Cores, and third-generation Tensor Cores, supports dual-card NVLink bridging, and is ideal for graphics rendering, virtual workstations (vGPU), and AI inference.
In Stock
Inventory:99itemSKU:NVIDIA-A40
Core Specifications
architecture
Ampere
Shape
PCIe Dual-Slot Full-Height Full-Length
GPU VRAM
48GB GDDR6 (ECC)
Memory Bandwidth
696 GB/s
FP32
37.4 TFLOPS
TF32 Tensor Core
149.7 TFLOPS* (sparse)
CompleteSpecifications
| architecture | Ampere |
| Shape | PCIe Dual-Slot Full-Height Full-Length |
| GPU VRAM | 48GB GDDR6 (ECC) |
| Memory Bandwidth | 696 GB/s |
| FP32 | 37.4 TFLOPS |
| TF32 Tensor Core | 149.7 TFLOPS* (sparse) |
| FP16 Tensor Core | 299.3 TFLOPS* (sparse) |
| RT Core | 2nd Generation |
| NVLink | Dual-card NVLink Bridge (112.5 GB/s) |
| Power Consumption | 300W |
| Location | Graphics Rendering, Virtual Workstations (vGPU), AI Inference |
