Nvidia P40
Compare prices for Nvidia P40 across cloud providers
July 12, 2024 (updated)
Released in 2016, the Nvidia P40 is designed for inference tasks and large-scale AI deployments. Its high memory bandwidth supports efficient model deployment in production environments.
| Provider | GPUs | VRAM | vCPUs | RAM | Price/h | |
|---|---|---|---|---|---|---|
Azure
|
1x P40 | 24GB | 6 | 112GB | $2.07 | Source |
|
Azure
|
2x P40 | 48GB | 12 | 224GB | $4.14 | Source |
|
Azure
|
4x P40 | 96GB | 24 | 448GB | $8.28 | Source |
|
Azure
|
4x P40 | 96GB | 24 | 448GB | $9.11 | Source |
Note: Prices are subject to change and may vary by region and other factors not listed here. For some GPUs, I include links to Shadeform (the sponsor) so you can check if they're available right now. I don’t earn a commission when you click on these links, but their monthly sponsorship helps me keep the site running.
Nvidia P40 specs
| GPU | 1 NVIDIA Pascal GPU |
| CUDA Cores | 3,840 |
| Memory Size | 24 GB GDDR5 |
| H.264 1080p30 streams | 24 |
| Max vGPU instances | 24 (1 GB Profile) |
| vGPU Profiles | 1 GB, 2 GB, 3 GB, 4 GB, 6 GB, 8 GB, 12 GB, 24 GB |
| Form Factor | PCIe 3.0 Dual Slot (rack servers) |
| Power | 250 W |
| Thermal | Passive |
Source: official Nvidia P40 datasheet.