A data center GPU against a consumer card, one Hopper and one Ampere: 80 GB HBM3 against 24 GB GDDR6X and 3.6x the memory bandwidth on the H100.
At a glance
Memory
- H100
- 80 GB
- RTX 3090
- 24 GB
3.3x more on H100
Memory bandwidth
- H100
- 3,350 GB/s
- RTX 3090
- 936 GB/s
3.6x higher on H100
Cheapest on-demand
- H100
- $1.30 /GPU/hr
- RTX 3090
- $0.10 /GPU/hr
13x more expensive on H100
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | H100 | RTX 3090 | Difference |
|---|---|---|---|
| On-demand | $3.33 /GPU/hr from $1.30 | $0.21 /GPU/hr from $0.10 | 16x more expensive on H100 |
| Reserved | $3.12 /GPU/hr from $1.53 (1 mo) | -- /GPU/hr from $0.06 (1 mo) | |
| Spot | $2.00 /GPU/hr from $0.42 | $0.12 /GPU/hr from $0.05 | 17x 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. No median for reserved on the RTX 3090: we only show one when at least 3 providers list the GPU on that billing type. Verify before provisioning. More on how we price.
Price history
H100 vs RTX 3090 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | H100 | RTX 3090 | 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 | 936 GB/s | 3.6x 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 | 71.2 TFLOPS | 14x higher on H100 |
| INT8 | 1,979 TOPS | 284.7 TOPS | 7x higher on H100 |
| FP32 | 67 TFLOPS | 35.6 TFLOPS | 1.9x higher on H100 |
| FP64 | 34 TFLOPS | Not supported | H100 only |
| Platform | |||
| Interconnect | NVLink 900 GB/s NVLink 600 GB/s on PCIe, NVL | NVLink 112 GB/s | 8x higher on H100 |
| Board power | 700 W | 350 W | 2x higher on H100 |
| Released | Q3 2022 | Q3 2020 | 2 years 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 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 /GPU/hr |
|---|---|---|
Lium
|
On-Demand $1.30 | On-Demand $0.16 |
HyperAI
|
On-Demand $1.80 | On-Demand $0.10 |
Vast.ai
|
On-Demand $1.73 | On-Demand $0.12 |
GPU.ai
|
On-Demand $1.98 | On-Demand $0.15 |
EmpirioLabs AI
|
On-Demand $2.60 | On-Demand $0.40 |
Koyeb
|
On-Demand $2.50 | -- |
Spheron
|
On-Demand $2.65 | -- |
Massed Compute
|
On-Demand $2.73 | -- |
Theta EdgeCloud
|
-- | On-Demand $0.13 |
Salad
|
-- | On-Demand $0.17 |
Runpod
|
-- | On-Demand $0.22 |
53 providers list the H100 and 10 the RTX 3090. Every listing is on the H100 page and the RTX 3090 page.
Similar GPUs
Other comparisons in the same class.
-
Nvidia B300
288 GB HBM3e · 2.4x the bandwidth of the H100
From $6.50 /GPU/hr Compare -
Nvidia H200
141 GB HBM3e · 43% more bandwidth than the H100
From $2.09 /GPU/hr Compare
-
Nvidia RTX 5090
32 GB GDDR7 · 47% less bandwidth than the H100
From $0.35 /GPU/hr Compare
-
Nvidia RTX 4090
24 GB GDDR6X · PCIe only
From $0.23 /GPU/hr Compare
Our data for Nvidia H100 was last updated on Sept. 14, 2026, and for Nvidia RTX 3090 on Sept. 14, 2026.