A data center GPU against a consumer card, one Ampere and one Kepler: 48 GB GDDR6 against 2 GB DDR3 and 50x the memory bandwidth on the A40.
At a glance
Updated 7 minutes ago- Memory
- 48 GB
- GDDR6
- Memory bandwidth
- 696 GB/s
- From
- $0.49 /GPU/hr
- 6 providers
- Memory
- 2 GB
- DDR3
- Memory bandwidth
- 14 GB/s
- From
- --
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | A40 | GT 730 | Difference |
|---|---|---|---|
| On-demand | $0.49 | -- | |
| Reserved | $0.61 | No reserved listings | |
| Median | $0.77 | -- |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
A40 vs GT 730 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | A40 | GT 730 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 48 GB GDDR6 | 2 GB DDR3 | 24x more on A40 |
| Bandwidth | 696 GB/s | 14 GB/s | 50x higher on A40 |
| Bus width | 384-bit | 64-bit | 6x wider on A40 |
| Compute · dense | |||
| FP16 / BF16 | 149.7 TFLOPS | Not supported | A40 only |
| INT8 | 299.3 TOPS | Not supported | A40 only |
| FP32 | 37.4 TFLOPS | 0.7 TFLOPS | 54x higher on A40 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 300 W | 23 W | 13x higher on A40 |
| Released | Q4 2020 | Q2 2014 | 6 years newer on A40 |
| Precision | |||
| Supported formats | FP16BF16TF32FP32INT4INT8 | FP32 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: A40 datasheet .
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | A40 /GPU/hr | GT 730 /GPU/hr |
|---|---|---|
Runpod
|
On-Demand $0.49 | -- |
Exoscale
|
On-Demand $1.05 | -- |
Database Mart
|
Reserved (24mo) $0.61 | -- |
Utho
|
Reserved (36mo) $0.65 | -- |
Sesterce
|
On-Demand $1.21 | -- |
EmpirioLabs AI
|
On-Demand $1.49 | -- |
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia A40 was last updated on Sept. 7, 2026, and for Nvidia GT 730 on Sept. 7, 2026.