Two Nvidia data center GPUs, one Ampere and one Turing: 48 GB GDDR6 against 16 GB GDDR6 and 2.2x the memory bandwidth on the A40.
At a glance
Memory
- A40
- 48 GB
- T4G
- 16 GB
3x more on A40
Memory bandwidth
- A40
- 696 GB/s
- T4G
- 320 GB/s
2.2x higher on A40
Cheapest on-demand
- A40
- $1.05 /GPU/hr
- T4G
- $0.42 /GPU/hr
2.5x more expensive on A40
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | A40 | T4G | Difference |
|---|---|---|---|
| On-demand | -- /GPU/hr from $1.05 | -- /GPU/hr from $0.42 | |
| Reserved | -- /GPU/hr from $0.61 (24 mo) | -- /GPU/hr from $0.18 (36 mo) |
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 on-demand and reserved on the A40 and on-demand and reserved on the T4G: 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
A40 vs T4G price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | A40 | T4G | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 48 GB GDDR6 | 16 GB GDDR6 | 3x more on A40 |
| Bandwidth | 696 GB/s | 320 GB/s | 2.2x higher on A40 |
| Bus width | 384-bit | 256-bit | 1.5x wider on A40 |
| Compute · dense | |||
| FP16 / BF16 | 149.7 TFLOPS | 65 TFLOPS | 2.3x higher on A40 |
| INT8 | 299.3 TOPS | 130 TOPS | 2.3x higher on A40 |
| FP32 | 37.4 TFLOPS | 8.1 TFLOPS | 4.6x higher on A40 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 300 W | 70 W | 4.3x higher on A40 |
| Released | Q4 2020 | Q3 2020 | |
| Precision | |||
| Supported formats | FP16BF16TF32FP32INT4INT8 | FP16FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: A40 datasheet and T4G datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | A40 /GPU/hr | T4G /GPU/hr |
|---|---|---|
Exoscale
|
On-Demand $1.05 | -- |
Database Mart
|
Reserved (24mo) $0.61 | -- |
Utho
|
Reserved (36mo) $0.65 | -- |
Runpod
|
Reservation on request | -- |
Sesterce
|
On-Demand $1.21 | -- |
EmpirioLabs AI
|
On-Demand $1.49 | -- |
AWS
|
-- | On-Demand $0.42 |
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia A40 was last updated on Sept. 7, 2026, and for Nvidia T4G on Sept. 7, 2026.