A data center GPU against a consumer card, one Ampere and one Blackwell: 24 GB HBM2 against 32 GB GDDR7 and 92% more memory bandwidth on the RTX 5090.
At a glance
Updated 6 minutes ago- Memory
- 24 GB
- HBM2
- Memory bandwidth
- 933 GB/s
- From
- $0.70 /GPU/hr
- 7 providers
- Memory
- 32 GB
- GDDR7
- Memory bandwidth
- 1.79 TB/s
- From
- $0.35 /GPU/hr
- 18 providers
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | A30 | RTX 5090 | Difference |
|---|---|---|---|
| On-demand | $0.70 | $0.35 | 2x more expensive on A30 |
| Spot | No spot listings | $0.25 | |
| Reserved | $0.43 | $0.21 | 2x more expensive on A30 |
| Median | $0.77 | $0.63 | 19% cheaper on RTX 5090 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
A30 vs RTX 5090 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | A30 | RTX 5090 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 24 GB HBM2 | 32 GB GDDR7 | 1.3x more on RTX 5090 |
| Bandwidth | 933 GB/s | 1,792 GB/s | 1.9x higher on RTX 5090 |
| Bus width | 512-bit | ||
| Compute · dense | |||
| FP4 | Not supported | 1,676 TFLOPS | RTX 5090 only |
| FP8 | Not supported | 419 TFLOPS | RTX 5090 only |
| FP16 / BF16 | 165 TFLOPS | 209.5 TFLOPS | 1.3x higher on RTX 5090 |
| INT8 | 330 TOPS | 838 TOPS | 2.5x higher on RTX 5090 |
| FP32 | 10.3 TFLOPS | 104.8 TFLOPS | 10x higher on RTX 5090 |
| FP64 | 5.2 TFLOPS | Not supported | A30 only |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 165 W | 575 W | 3.5x higher on RTX 5090 |
| Released | Q2 2021 | Q1 2025 | 4 years newer on RTX 5090 |
| Precision | |||
| Supported formats | FP16BF16TF32FP32FP64INT4INT8 | FP4FP8FP16BF16TF32FP32INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: A30 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 | A30 /GPU/hr | RTX 5090 /GPU/hr |
|---|---|---|
Leafcloud
|
On-Demand $0.70 | -- |
Exoscale
|
On-Demand $0.74 | -- |
Leaseweb
|
Reserved (1mo) $0.43 | -- |
AceCloud
|
Reserved (12mo) $0.67 | -- |
Massed Compute
|
On-Demand $0.35 | -- |
Sesterce
|
On-Demand $0.39 | -- |
EmpirioLabs AI
|
On-Demand $0.55 | -- |
HyperAI
|
-- | On-Demand $0.35 |
Salad
|
-- | On-Demand $0.45 |
GPUhub
|
-- | On-Demand $0.46 |
Nova Cloud
|
-- | On-Demand $0.63 |
Vast.ai
|
-- | On-Demand $0.73 |
GPU.ai
|
-- | On-Demand $53.34 |
GPUaaS
|
-- | Custom on request |
SwissGPU
|
-- | On-Demand $0.61 |
7 providers list the A30 and 18 the RTX 5090. Every listing is on the A30 page and the RTX 5090 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia A30 was last updated on Sept. 7, 2026, and for Nvidia RTX 5090 on Sept. 7, 2026.