A consumer GPU against a workstation card on the Pascal architecture: 8 GB GDDR5X against 2 GB GDDR5 and 4x the memory bandwidth on the GTX 1080.
At a glance
Updated 7 minutes ago- Memory
- 8 GB
- GDDR5X
- Memory bandwidth
- 320 GB/s
- From
- $0.04 /GPU/hr
- 2 providers
- Memory
- 2 GB
- GDDR5
- Memory bandwidth
- 80 GB/s
- From
- --
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | GTX 1080 | P620 | Difference |
|---|---|---|---|
| On-demand | $0.04 | -- | |
| Spot | $0.02 | No spot listings | |
| Median | $0.04 | -- |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
GTX 1080 vs P620 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | GTX 1080 | P620 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 8 GB GDDR5X | 2 GB GDDR5 | 4x more on GTX 1080 |
| Bandwidth | 320 GB/s | 80 GB/s | 4x higher on GTX 1080 |
| Bus width | 256-bit | 128-bit | 2x wider on GTX 1080 |
| Compute · dense | |||
| FP32 | 8.9 TFLOPS | 1.3 TFLOPS | 6.8x higher on GTX 1080 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 180 W | 40 W | 4.5x higher on GTX 1080 |
| Released | Q2 2016 | Q1 2018 | 2 years newer on P620 |
| Precision | |||
| Supported formats | FP16FP32 | FP16FP32 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: GTX 1080 datasheet and P620 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | GTX 1080 /GPU/hr | P620 /GPU/hr |
|---|---|---|
Salad
|
On-Demand $0.0400 | -- |
Vast.ai
|
On-Demand $0.0472 | -- |
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia GTX 1080 was last updated on Sept. 7, 2026, and for Nvidia P620 on Sept. 7, 2026.