The H800 is newer, with 3.3x the memory and 2.1x the bandwidth.
At a glance
Memory
3.3x more on H800
- A30
- 24 GB
- H800
- 80 GB
Memory bandwidth
2.1x higher on H800
- A30
- 933 GB/s
- H800
- 2,000 GB/s
Cheapest on-demand
- A30
- $0.33 /GPU/hr
- H800
- --
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | A30 | H800 | Difference |
|---|---|---|---|
| On-demand | $0.76 /GPU/hr from $0.33 | No on-demand listings | |
| Reserved | $0.56 /GPU/hr from $0.28 (12 mo) | No reserved listings | |
| Spot | Sold out | 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. Verify before provisioning. More on how we price.
Price history
A30 vs H800 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | A30 | H800 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 24 GB HBM2 | 80 GB HBM2e | 3.3x more on H800 |
| Bandwidth | 933 GB/s | 2,000 GB/s | 2.1x higher on H800 |
| Bus width | 5,120-bit | ||
| Compute · dense | |||
| FP8 | Not supported | 1,513 TFLOPS | H800 only |
| FP16 / BF16 | 165 TFLOPS | 756.5 TFLOPS | 4.6x higher on H800 |
| INT8 | 330 TOPS | 1,513 TOPS | 4.6x higher on H800 |
| FP32 | 10.3 TFLOPS | 51 TFLOPS | 5x higher on H800 |
| FP64 | 5.2 TFLOPS | ||
| Platform | |||
| Interconnect | PCIe only | NVLink 400 GB/s | NVLink on H800 only |
| Board power | 165 W | 350 W | 2.1x higher on H800 |
| Released | Q2 2021 | Q1 2023 | 2 years newer on H800 |
| Precision | |||
| Supported formats | FP16BF16TF32FP32FP64INT4INT8 | FP8FP16BF16TF32FP32FP64INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: A30 datasheet .
Where to rent them
Providers that rent these GPUs, with each one's cheapest rate. No provider we track offers both right now.
| Provider | A30 | H800 |
|---|---|---|
Leafcloud
Netherlands
|
$0.68 /GPU/hr On-demand PCIe | -- |
Seeweb
Italy
|
$0.33 /GPU/hr On-demand PCIe | -- |
Exoscale
Switzerland
|
$0.74 /GPU/hr On-demand | -- |
E2E Networks
India
|
$0.96 /GPU/hr On-demand | -- |
Leaseweb
Netherlands
|
$0.46 /GPU/hr Reserved | -- |
AceCloud
India
|
$0.67 /GPU/hr Reserved | -- |
Massed Compute
USA
|
$0.35 /GPU/hr On-demand | -- |
Sesterce
France
|
$0.39 /GPU/hr On-demand | -- |
10 providers list the A30 and 0 the H800. Every listing is on the A30 page and the H800 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia A30 was last updated on Sept. 14, 2026, and for Nvidia H800 on Sept. 14, 2026.