A data center GPU against a consumer card, one Grace Hopper and one Blackwell: 96 GB HBM3 against 32 GB GDDR7, 2.2x the memory bandwidth on the GH200, and NVLink 900 GB/s on the GH200 where the RTX 5090 is PCIe only.
At a glance
Updated 7 minutes ago- Memory
- 96 GB
- HBM3
- Memory bandwidth
- 4.00 TB/s
- From
- $6.50 /GPU/hr
- 4 providers
- Memory
- 32 GB
- GDDR7
- Memory bandwidth
- 1.79 TB/s
- From
- $0.35 /GPU/hr
- 20 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | GH200 | RTX 5090 | Difference |
|---|---|---|---|
| On-demand | $6.50 | $0.35 | 19x more expensive on GH200 |
| Spot | No spot listings | $0.25 | |
| Reserved | No reserved listings | $0.21 | |
| Median | $6.50 | $0.69 | 9.4x more expensive on GH200 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
GH200 vs RTX 5090 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | GH200 | RTX 5090 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 96 GB HBM3 | 32 GB GDDR7 | 3x more on GH200 |
| Bandwidth | 4,000 GB/s | 1,792 GB/s | 2.2x higher on GH200 |
| Bus width | 512-bit | ||
| Compute · dense | |||
| FP4 | Not supported | 1,676 TFLOPS | RTX 5090 only |
| FP8 | 1,979 TFLOPS | 419 TFLOPS | 4.7x higher on GH200 |
| FP16 / BF16 | 989.5 TFLOPS | 209.5 TFLOPS | 4.7x higher on GH200 |
| INT8 | 1,979 TOPS | 838 TOPS | 2.4x higher on GH200 |
| FP32 | 67 TFLOPS | 104.8 TFLOPS | 1.6x higher on RTX 5090 |
| FP64 | 34 TFLOPS | Not supported | GH200 only |
| Platform | |||
| Interconnect | NVLink 900 GB/s | PCIe only | NVLink on GH200 only |
| Released | Q2 2023 | Q1 2025 | 2 years newer on RTX 5090 |
| Precision | |||
| Supported formats | FP8FP16BF16TF32FP32FP64INT8 | FP4FP8FP16BF16TF32FP32INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: GH200 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 | GH200 /GPU/hr | RTX 5090 /GPU/hr |
|---|---|---|
CoreWeave
|
On-Demand $6.50 | -- |
Lambda Labs
|
On-Demand $2.29 | -- |
Sesterce
|
On-Demand $2.52 | -- |
Vultr
|
Spot $1.99 | -- |
HyperAI
|
-- | On-Demand $0.35 |
Salad
|
-- | On-Demand $0.45 |
GPUhub
|
-- | On-Demand $0.46 |
Nova Cloud
|
-- | On-Demand $0.63 |
Lium
|
-- | On-Demand $0.69 |
Theta EdgeCloud
|
-- | On-Demand $0.82 |
Vast.ai
|
-- | On-Demand $10.67 |
GPU.ai
|
-- | On-Demand $53.34 |
4 providers list the GH200 and 20 the RTX 5090. Every listing is on the GH200 page and the RTX 5090 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia GH200 was last updated on Sept. 7, 2026, and for Nvidia RTX 5090 on Sept. 7, 2026.