A data center GPU against a consumer card, one Hopper and one Ada Lovelace: 80 GB HBM2e against 12 GB GDDR6X, 4x the memory bandwidth on the H800, and NVLink 400 GB/s on the H800 where the RTX 4070 is PCIe only.
At a glance
Updated 8 minutes ago- Memory
- 80 GB
- HBM2e
- Memory bandwidth
- 2.00 TB/s
- From
- --
- Memory
- 12 GB
- GDDR6X
- Memory bandwidth
- 504 GB/s
- From
- $0.17 /GPU/hr
- 2 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | H800 | RTX 4070 | Difference |
|---|---|---|---|
| On-demand | -- | $0.17 | |
| Spot | No spot listings | $0.07 | |
| Median | -- | $0.21 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
H800 vs RTX 4070 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | H800 | RTX 4070 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 80 GB HBM2e | 12 GB GDDR6X | 6.7x more on H800 |
| Bandwidth | 2,000 GB/s | 504 GB/s | 4x higher on H800 |
| Bus width | 5,120-bit | 192-bit | 27x wider on H800 |
| Compute · dense | |||
| FP8 | 1,513 TFLOPS | 116.6 TFLOPS | 13x higher on H800 |
| FP16 / BF16 | 756.5 TFLOPS | 58.3 TFLOPS | 13x higher on H800 |
| INT8 | 1,513 TOPS | 233.2 TOPS | 6.5x higher on H800 |
| FP32 | 51 TFLOPS | 29.1 TFLOPS | 1.8x higher on H800 |
| Platform | |||
| Interconnect | NVLink 400 GB/s | PCIe only | NVLink on H800 only |
| Board power | 350 W | 200 W | 1.8x higher on H800 |
| Released | Q1 2023 | Q2 2023 | |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32FP64INT8 | FP8FP16BF16TF32FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: RTX 4070 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | H800 /GPU/hr | RTX 4070 /GPU/hr |
|---|---|---|
Theta EdgeCloud
|
-- | On-Demand $0.17 |
Salad
|
-- | On-Demand $0.22 |
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia H800 was last updated on Sept. 7, 2026, and for Nvidia RTX 4070 on Sept. 7, 2026.