AMD Radeon Pro V520
vs
Intel Gaudi2
Two data center GPUs, one RDNA and one Gaudi (2nd Gen): 8 GB HBM2 against 96 GB HBM2e, 4.8x the memory bandwidth on the Gaudi2, and RoCE 600 GB/s on the Gaudi2 where the Radeon Pro V520 is PCIe only.
At a glance
Memory
- Radeon Pro V520
- 8 GB
- Gaudi2
- 96 GB
12x more on Gaudi2
Memory bandwidth
- Radeon Pro V520
- 512 GB/s
- Gaudi2
- 2,450 GB/s
4.8x higher on Gaudi2
Cheapest on-demand
- Radeon Pro V520
- $0.38 /GPU/hr
- Gaudi2
- $1.03 /GPU/hr
2.7x more expensive on Gaudi2
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | Radeon Pro V520 | Gaudi2 | Difference |
|---|---|---|---|
| On-demand | -- /GPU/hr from $0.38 | $1.21 /GPU/hr from $1.03 | |
| Reserved | -- /GPU/hr from $0.19 (36 mo) | -- /GPU/hr from $0.58 (12 mo) |
Heads up: A provider's own page may quote a different figure, for example on tax, region or a promotion. A monthly-only plan shows a derived hourly rate. Medians are across providers, one vote each, so a large catalog does not outweigh a small one. No median for on-demand and reserved on the Radeon Pro V520 and reserved on the Gaudi2: we only show one when at least 3 providers list the GPU on that billing type. Verify before provisioning. More on how we price.
Price history
Radeon Pro V520 vs Gaudi2 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | Radeon Pro V520 | Gaudi2 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 8 GB HBM2 | 96 GB HBM2e | 12x more on Gaudi2 |
| Bandwidth | 512 GB/s | 2,450 GB/s | 4.8x higher on Gaudi2 |
| Bus width | 2,048-bit | ||
| Compute · dense | |||
| FP8 | Not supported | 865 TFLOPS | Gaudi2 only |
| FP16 / BF16 | 14.8 TFLOPS | 432 TFLOPS | 29x higher on Gaudi2 |
| FP32 | 7.4 TFLOPS | ||
| Platform | |||
| Interconnect | PCIe only | RoCE 600 GB/s | RoCE on Gaudi2 only |
| Board power | 225 W | 600 W | 2.7x higher on Gaudi2 |
| Released | Q2 2020 | Q2 2022 | 2 years newer on Gaudi2 |
| Precision | |||
| Supported formats | FP16FP32INT4INT8 | FP8FP16BF16TF32FP32INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: Radeon Pro V520 datasheet and Gaudi2 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 | Gaudi2 /GPU/hr |
|---|---|---|
|
|
On-Demand $0.38 | -- |
|
|
-- | On-Demand $1.21 |
|
|
-- | On-Demand $1.21 |
|
|
-- | On-Demand $1.03 |
Similar GPUs
Other comparisons in the same class.
-
Nvidia A10G
From $1.00 /GPU/hr Compare -
Nvidia M60
From $0.75 /GPU/hr Compare -
Nvidia H100
From $1.55 /GPU/hr Compare -
Nvidia A100
From $0.80 /GPU/hr Compare
Our data for AMD Radeon Pro V520 was last updated on Sept. 7, 2026, and for Intel Gaudi2 on Sept. 7, 2026.