A data center GPU against a workstation card, one Hopper and one Turing: 80 GB HBM3 against 16 GB GDDR6 and 7.5x the memory bandwidth on the H100.
At a glance
Updated 3 minutes ago- Memory
- 80 GB
- HBM3 · 94 GB on NVL
- Memory bandwidth
- 3.35 TB/s
- 2,000 GB/s on PCIe · 3,938 GB/s on NVL
- From
- $1.50 /GPU/hr
- 53 providers
- Memory
- 16 GB
- GDDR6
- Memory bandwidth
- 448 GB/s
- From
- $0.60 /GPU/hr
- 2 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | H100 | RTX 5000 | Difference |
|---|---|---|---|
| On-demand | $1.50 | $0.60 | 2.5x more expensive on H100 |
| Spot | $0.35 | No spot listings | |
| Reserved | $1.18 | No reserved listings | |
| Median | $3.37 | $0.71 | 4.7x more expensive on H100 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
H100 vs RTX 5000 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | H100 | RTX 5000 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 80 GB HBM3 94 GB on NVL | 16 GB GDDR6 | 5x more on H100 |
| Bandwidth | 3,350 GB/s 2,000 GB/s on PCIe 3,938 GB/s on NVL | 448 GB/s | 7.5x higher on H100 |
| Bus width | 5,120-bit | 256-bit | 20x wider on H100 |
| Compute · dense | |||
| FP8 | 1,979 TFLOPS | Not supported | H100 only |
| FP16 / BF16 | 989.5 TFLOPS | 89.2 TFLOPS | 11x higher on H100 |
| INT8 | 1,979 TOPS | 178.4 TOPS | 11x higher on H100 |
| FP32 | 67 TFLOPS | 11.2 TFLOPS | 6x higher on H100 |
| FP64 | 34 TFLOPS | Not supported | H100 only |
| Platform | |||
| Interconnect | NVLink 900 GB/s NVLink 600 GB/s on PCIe, NVL | NVLink 50 GB/s | 18x higher on H100 |
| Board power | 700 W | 265 W | 2.6x higher on H100 |
| Released | Q3 2022 | Q3 2018 | 4 years newer on H100 |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32FP64INT8 | FP16FP32INT4INT8 | |
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 5000 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 5000 /GPU/hr |
|---|---|---|
Lium
|
On-Demand $1.50 | -- |
Vast.ai
|
On-Demand $1.73 | -- |
HyperAI
|
On-Demand $1.80 | -- |
UpCloud
|
On-Demand $1.89 | -- |
GPU.ai
|
On-Demand $1.98 | -- |
Sesterce
|
On-Demand $2.19 | -- |
Runcrate
|
On-Demand $2.19 | -- |
Koyeb
|
On-Demand $2.50 | -- |
OVH
|
-- | On-Demand $0.60 |
Paperspace
|
-- | On-Demand $0.82 |
53 providers list the H100 and 2 the RTX 5000. Every listing is on the H100 page and the RTX 5000 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia H100 was last updated on Sept. 7, 2026, and for Nvidia RTX 5000 on Sept. 7, 2026.