A data center GPU against a consumer card, one Ampere and one Blackwell: 24 GB GDDR6 against 32 GB GDDR7 and 3x the memory bandwidth on the RTX 5090.
At a glance
Updated 6 minutes ago- Memory
- 24 GB
- GDDR6
- Memory bandwidth
- 600 GB/s
- From
- $1.00 /GPU/hr
- 8 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 | A10 | RTX 5090 | Difference |
|---|---|---|---|
| On-demand | $1.00 | $0.35 | 2.9x more expensive on A10 |
| Spot | $0.60 | $0.25 | 2.4x more expensive on A10 |
| Reserved | $0.71 | $0.21 | 3.4x more expensive on A10 |
| Median | $1.42 | $0.63 | 2.3x more expensive on A10 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
A10 vs RTX 5090 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | A10 | RTX 5090 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 24 GB GDDR6 | 32 GB GDDR7 | 1.3x more on RTX 5090 |
| Bandwidth | 600 GB/s | 1,792 GB/s | 3x higher on RTX 5090 |
| Bus width | 384-bit | 512-bit | 1.3x wider on RTX 5090 |
| Compute · dense | |||
| FP4 | Not supported | 1,676 TFLOPS | RTX 5090 only |
| FP8 | Not supported | 419 TFLOPS | RTX 5090 only |
| FP16 / BF16 | 125 TFLOPS | 209.5 TFLOPS | 1.7x higher on RTX 5090 |
| INT8 | 250 TOPS | 838 TOPS | 3.4x higher on RTX 5090 |
| FP32 | 31.2 TFLOPS | 104.8 TFLOPS | 3.4x higher on RTX 5090 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 150 W | 575 W | 3.8x higher on RTX 5090 |
| Released | Q2 2021 | Q1 2025 | 4 years newer on RTX 5090 |
| Precision | |||
| Supported formats | FP16BF16TF32FP32INT4INT8 | FP4FP8FP16BF16TF32FP32INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: A10 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 | A10 /GPU/hr | RTX 5090 /GPU/hr |
|---|---|---|
Lambda Labs
|
On-Demand $1.29 | -- |
Sesterce
|
On-Demand $1.42 | -- |
Runcrate
|
On-Demand $1.42 | -- |
OVH
|
On-Demand $1.00 | -- |
Cerebrium
|
On-Demand $1.10 | -- |
Alibaba Cloud
|
On-Demand $1.27 | -- |
Oracle Cloud
|
On-Demand $2.00 | -- |
Azure
|
On-Demand $3.20 | -- |
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 |
8 providers list the A10 and 18 the RTX 5090. Every listing is on the A10 page and the RTX 5090 page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia A10 was last updated on Sept. 7, 2026, and for Nvidia RTX 5090 on Sept. 7, 2026.