Nvidia T4
Compare prices for Nvidia T4 across cloud providers
Oct. 14, 2024 (updated)
Released in 2018, the Nvidia T4 is designed for scalable AI inference and analytics. It is widely used in cloud environments for real-time AI applications due to its energy efficiency.
| Provider | GPUs | VRAM | vCPUs | RAM | Price/h | |
|---|---|---|---|---|---|---|
Azure
|
1x T4 | 16GB | 4 | 28GB | $0.53 | Source |
|
Azure
|
1x T4 | 16GB | 8 | 56GB | $0.75 | Source |
Replicate
|
1x T4 | 16GB | 4 | 16GB | $0.81 | Source |
Alibaba Cloud
|
1x T4 | 16GB | 4 | 15GB | $1.18 | Source |
|
Azure
|
1x T4 | 16GB | 16 | 110GB | $1.20 | Source |
|
Azure
|
4x T4 | 64GB | 64 | 440GB | $4.35 | 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 T4 specs
| GPU Architecture | NVIDIA Turing |
| NVIDIA Turing Tensor Cores | 320 |
| NVIDIA CUDA® Cores | 2,560 |
| Single-Precision | 8.1 TFLOPS |
| Mixed-Precision (FP16/FP32) | 65 TFLOPS |
| INT8 | 130 TOPS |
| INT4 | 260 TOPS |
| GPU Memory | 16 GB GDDR6 |
| Memory Bandwidth | 300 GB/sec |
| ECC | Yes |
| Interconnect Bandwidth | 32 GB/sec |
| System Interface | x16 PCIe Gen3 |
| Form Factor | Low-Profile PCIe |
| Thermal Solution | Passive |
| Compute APIs | CUDA, NVIDIA TensorRT™, ONNX |
Source: official Nvidia T4 datasheet.