Two Nvidia data center GPUs, one Ampere and one Turing: 24 GB GDDR6 against 16 GB GDDR6 and 88% more memory bandwidth on the A10G.
At a glance
Updated 7 hours ago- Memory
- 24 GB
- GDDR6
- Memory bandwidth
- 600 GB/s
- From
- $1.00 /GPU/hr
- 2 providers
- Memory
- 16 GB
- GDDR6
- Memory bandwidth
- 320 GB/s
- From
- $0.42 /GPU/hr
- 1 provider
Price comparison
Cheapest listed price per GPU per hour by billing type, and the median across providers.
| Billing | A10G | T4G | Difference |
|---|---|---|---|
| On-demand | $1.00 | $0.42 | 2.4x more expensive on A10G |
| Reserved | $0.43 | $0.18 | 2.4x more expensive on A10G |
| Median | $1.60 | $1.10 | 31% cheaper on T4G |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
A10G vs T4G price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | A10G | T4G | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 24 GB GDDR6 | 16 GB GDDR6 | 1.5x more on A10G |
| Bandwidth | 600 GB/s | 320 GB/s | 1.9x higher on A10G |
| Bus width | 256-bit | ||
| Compute · dense | |||
| FP16 / BF16 | 70 TFLOPS | 65 TFLOPS | 1.1x higher on A10G |
| INT8 | 140 TOPS | 130 TOPS | 1.1x higher on A10G |
| FP32 | 35 TFLOPS | 8.1 TFLOPS | 4.3x higher on A10G |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 300 W | 70 W | 4.3x higher on A10G |
| Released | Q2 2021 | Q3 2020 | 7 months newer on A10G |
| Precision | |||
| Supported formats | FP16BF16TF32FP32INT4INT8 | FP16FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: A10G datasheet and T4G datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | A10G /GPU/hr | T4G /GPU/hr |
|---|---|---|
|
|
On-Demand $1.01 | On-Demand $0.42 |
|
|
On-Demand $1.00 | -- |
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia A10G was last updated on Sept. 7, 2026, and for Nvidia T4G on Sept. 7, 2026.