A data center GPU against a workstation card, one Grace Blackwell and one Pascal: 186 GB HBM3e against 2 GB GDDR5, 100x the memory bandwidth on the GB200, and NVLink 1,800 GB/s on the GB200 where the P620 is PCIe only.
At a glance
Memory
- GB200
- 186 GB
- P620
- 2 GB
93x more on GB200
Memory bandwidth
- GB200
- 8,000 GB/s
- P620
- 80 GB/s
100x higher on GB200
Cheapest on-demand
- GB200
- $10.50 /GPU/hr
- P620
- --
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | GB200 | P620 | Difference |
|---|---|---|---|
| On-demand | $16.00 /GPU/hr from $10.50 | No on-demand listings | |
| Reserved | -- /GPU/hr from $10.58 | No reserved listings | |
| Spot | -- /GPU/hr from $27.04 | No spot listings |
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 reserved and spot on the GB200: 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
GB200 vs P620 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | GB200 | P620 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 186 GB HBM3e | 2 GB GDDR5 | 93x more on GB200 |
| Bandwidth | 8,000 GB/s | 80 GB/s | 100x higher on GB200 |
| Bus width | 128-bit | ||
| Compute · dense | |||
| FP4 | 10,000 TFLOPS | Not supported | GB200 only |
| FP8 | 5,000 TFLOPS | Not supported | GB200 only |
| FP16 / BF16 | 2,500 TFLOPS | ||
| INT8 | 5,000 TOPS | Not supported | GB200 only |
| FP32 | 80 TFLOPS | 1.3 TFLOPS | 62x higher on GB200 |
| FP64 | 40 TFLOPS | Not supported | GB200 only |
| Platform | |||
| Interconnect | NVLink 1,800 GB/s | PCIe only | NVLink on GB200 only |
| Board power | 1,200 W | 40 W | 30x higher on GB200 |
| Released | Q1 2024 | Q1 2018 | 6 years newer on GB200 |
| Precision | |||
| Supported formats | FP4FP6FP8FP16BF16TF32FP32FP64INT8 | FP16FP32 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: GB200 datasheet and P620 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | GB200 /GPU/hr | P620 /GPU/hr |
|---|---|---|
CoreWeave
|
On-Demand $10.50 | -- |
Oracle Cloud
|
On-Demand $16.00 | -- |
Azure
|
On-Demand $27.04 | -- |
AWS
|
Reservation $10.58 | -- |
CUDO
|
Custom on request | -- |
Canopy Wave
|
Custom on request | -- |
Nebius
|
Custom on request | -- |
Together AI
|
Custom on request | -- |
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia GB200 was last updated on Sept. 7, 2026, and for Nvidia P620 on Sept. 7, 2026.