AMD Radeon Pro V520
vs
Nvidia GTX 1070 Ti
A data center GPU against a consumer card, one RDNA and one Pascal: 8 GB HBM2 against 8 GB GDDR5 and 2x the memory bandwidth on the Radeon Pro V520.
At a glance
Updated 13 hours ago- Memory
- 8 GB
- HBM2
- Memory bandwidth
- 512 GB/s
- From
- $0.38 /GPU/hr
- 1 provider
- Memory
- 8 GB
- GDDR5
- Memory bandwidth
- 256 GB/s
- From
- --
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | Radeon Pro V520 | GTX 1070 Ti | Difference |
|---|---|---|---|
| On-demand | $0.38 | -- | |
| Reserved | $0.19 | No reserved listings | |
| Median | $0.87 | -- |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
Radeon Pro V520 vs GTX 1070 Ti price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | Radeon Pro V520 | GTX 1070 Ti | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 8 GB HBM2 | 8 GB GDDR5 | Identical |
| Bandwidth | 512 GB/s | 256 GB/s | 2x higher on Radeon Pro V520 |
| Bus width | 2,048-bit | 256-bit | 8x wider on Radeon Pro V520 |
| Compute · dense | |||
| FP16 / BF16 | 14.8 TFLOPS | ||
| FP32 | 7.4 TFLOPS | 8.2 TFLOPS | 1.1x higher on GTX 1070 Ti |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 225 W | 180 W | 1.2x higher on Radeon Pro V520 |
| Released | Q2 2020 | Q4 2017 | 2 years newer on Radeon Pro V520 |
| Precision | |||
| Supported formats | FP16FP32INT4INT8 | FP16FP32 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: Radeon Pro V520 datasheet and GTX 1070 Ti datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | Radeon Pro V520 /GPU/hr | GTX 1070 Ti /GPU/hr |
|---|---|---|
AWS
|
On-Demand $0.38 | -- |
Similar GPUs
Other comparisons in the same class.
Our data for AMD Radeon Pro V520 was last updated on Sept. 7, 2026, and for Nvidia GTX 1070 Ti on Sept. 7, 2026.