A data center GPU against a consumer card, one Hopper and one Blackwell: 80 GB HBM3 against 32 GB GDDR7, 87% more memory bandwidth on the H100, and NVLink 900 GB/s on the H100 where the RTX 5090 is PCIe only.
At a glance
Memory
- H100
- 80 GB
- RTX 5090
- 32 GB
2.5x more on H100
Memory bandwidth
- H100
- 3.35 TB/s
- RTX 5090
- 1.79 TB/s
1.9x higher on H100
Cheapest on-demand
- H100
- $1.41 /GPU/hr
- RTX 5090
- $0.35 /GPU/hr
4x more expensive on H100
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | H100 | RTX 5090 | Difference |
|---|---|---|---|
| On-demand | $3.33 /GPU/hr from $1.41 | $0.72 /GPU/hr from $0.35 | 4.6x more expensive on H100 |
| Reserved | $3.11 /GPU/hr from $1.53 (1 mo) | $0.58 /GPU/hr from $0.21 (1 mo) | 5.4x more expensive on H100 |
| Spot | $2.00 /GPU/hr from $0.69 | $0.40 /GPU/hr from $0.20 | 5x more expensive on H100 |
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
H100 vs RTX 5090 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | H100 | RTX 5090 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 80 GB HBM3 94 GB on NVL | 32 GB GDDR7 | 2.5x more on H100 |
| Bandwidth | 3,350 GB/s 2,000 GB/s on PCIe 3,938 GB/s on NVL | 1,792 GB/s | 1.9x higher on H100 |
| Bus width | 5,120-bit | 512-bit | 10x wider on H100 |
| Compute · dense | |||
| FP4 | Not supported | 1,676 TFLOPS | RTX 5090 only |
| FP8 | 1,979 TFLOPS | 419 TFLOPS | 4.7x higher on H100 |
| FP16 / BF16 | 989.5 TFLOPS | 209.5 TFLOPS | 4.7x higher on H100 |
| INT8 | 1,979 TOPS | 838 TOPS | 2.4x higher on H100 |
| FP32 | 67 TFLOPS | 104.8 TFLOPS | 1.6x higher on RTX 5090 |
| FP64 | 34 TFLOPS | Not supported | H100 only |
| Platform | |||
| Interconnect | NVLink 900 GB/s NVLink 600 GB/s on PCIe, NVL | PCIe only | NVLink on H100 only |
| Board power | 700 W | 575 W | 1.2x higher on H100 |
| Released | Q3 2022 | Q1 2025 | 2 years newer on RTX 5090 |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32FP64INT8 | FP4FP8FP16BF16TF32FP32INT8 | |
Figures are for each model's headline configuration. Where a form factor carries a different number, it is named under the figure.
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: H100 datasheet and RTX 5090 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | H100 /GPU/hr | RTX 5090 /GPU/hr |
|---|---|---|
Lium
|
On-Demand $1.41 | On-Demand $0.45 |
HyperAI
|
On-Demand $1.80 | On-Demand $0.35 |
Vast.ai
|
On-Demand $1.73 | On-Demand $0.40 |
GPU.ai
|
On-Demand $1.98 | On-Demand $0.44 |
Runpod
|
On-Demand $2.59 | On-Demand $0.69 |
Koyeb
|
On-Demand $2.50 | -- |
Spheron
|
On-Demand $2.65 | -- |
Massed Compute
|
On-Demand $2.73 | -- |
GPUhub
|
-- | On-Demand $0.46 |
Salad
|
-- | On-Demand $0.50 |
Nova Cloud
|
-- | On-Demand $0.63 |
53 providers list the H100 and 21 the RTX 5090. Every listing is on the H100 page and the RTX 5090 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia B300
From $6.50 /GPU/hr Compare -
Nvidia H200
From $2.09 /GPU/hr Compare -
Nvidia A100
From $0.40 /GPU/hr Compare -
Nvidia RTX PRO 6000
From $0.66 /GPU/hr Compare -
Nvidia RTX 4090
From $0.23 /GPU/hr Compare
Our data for Nvidia H100 was last updated on Sept. 14, 2026, and for Nvidia RTX 5090 on Sept. 14, 2026.