A data center GPU against a consumer card, one Hopper and one Ampere: 80 GB HBM3 against 24 GB GDDR6X, 3.3x the memory bandwidth on the H100, and NVLink 900 GB/s on the H100 where the RTX 3090 Ti is PCIe only.
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
- 24 GB
- GDDR6X
- Memory bandwidth
- 1.01 TB/s
- From
- $0.23 /GPU/hr
- 3 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | H100 | RTX 3090 Ti | Difference |
|---|---|---|---|
| On-demand | $1.50 | $0.23 | 6.6x more expensive on H100 |
| Spot | $0.35 | $0.10 | 3.5x more expensive on H100 |
| Reserved | $1.18 | No reserved listings | |
| Median | $3.37 | $0.25 | 13x 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 3090 Ti price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | H100 | RTX 3090 Ti | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 80 GB HBM3 94 GB on NVL | 24 GB GDDR6X | 3.3x more on H100 |
| Bandwidth | 3,350 GB/s 2,000 GB/s on PCIe 3,938 GB/s on NVL | 1,008 GB/s | 3.3x higher on H100 |
| Bus width | 5,120-bit | 384-bit | 13x wider on H100 |
| Compute · dense | |||
| FP8 | 1,979 TFLOPS | Not supported | H100 only |
| FP16 / BF16 | 989.5 TFLOPS | 80 TFLOPS | 12x higher on H100 |
| INT8 | 1,979 TOPS | 320 TOPS | 6.2x higher on H100 |
| FP32 | 67 TFLOPS | 40 TFLOPS | 1.7x higher on H100 |
| 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 | 450 W | 1.6x higher on H100 |
| Released | Q3 2022 | Q1 2022 | 6 months newer on H100 |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32FP64INT8 | FP16BF16TF32FP32INT4INT8 | |
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 3090 Ti 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 3090 Ti /GPU/hr |
|---|---|---|
Vast.ai
|
On-Demand $1.73 | On-Demand $0.23 |
Lium
|
On-Demand $1.50 | -- |
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 | -- |
Salad
|
-- | On-Demand $0.28 |
Runpod
|
-- | On-Demand $0.27 |
53 providers list the H100 and 3 the RTX 3090 Ti. Every listing is on the H100 page and the RTX 3090 Ti 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 3090 Ti on Sept. 7, 2026.