Two Nvidia data center GPUs, one Ampere and one Turing: 80 GB HBM2e against 16 GB GDDR6, 6x the memory bandwidth on the A100, and NVLink 600 GB/s on the A100 where the T4G is PCIe only.
At a glance
Memory
- A100
- 80 GB
- T4G
- 16 GB
5x more on A100
Memory bandwidth
- A100
- 1,935 GB/s
- T4G
- 320 GB/s
6x higher on A100
Cheapest on-demand
- A100
- $0.89 /GPU/hr
- T4G
- $0.42 /GPU/hr
2.1x more expensive on A100
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | A100 | T4G | Difference |
|---|---|---|---|
| On-demand | $1.81 /GPU/hr from $0.89 | -- /GPU/hr from $0.42 | |
| Reserved | $1.60 /GPU/hr from $0.66 (24 mo) | -- /GPU/hr from $0.18 (36 mo) | |
| Spot | $1.20 /GPU/hr from $0.67 | No spot listings |
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 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
A100 vs T4G price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | A100 | T4G | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 80 GB HBM2e 40 GB on SXM, PCIe | 16 GB GDDR6 | 5x more on A100 |
| Bandwidth | 1,935 GB/s 2,039 GB/s on SXM 1,555 GB/s on SXM, PCIe | 320 GB/s | 6x higher on A100 |
| Bus width | 5,120-bit | 256-bit | 20x wider on A100 |
| Compute · dense | |||
| FP16 / BF16 | 312 TFLOPS | 65 TFLOPS | 4.8x higher on A100 |
| INT8 | 624 TOPS | 130 TOPS | 4.8x higher on A100 |
| FP32 | 19.5 TFLOPS | 8.1 TFLOPS | 2.4x higher on A100 |
| FP64 | 9.7 TFLOPS | Not supported | A100 only |
| Platform | |||
| Interconnect | NVLink 600 GB/s | PCIe only | NVLink on A100 only |
| Board power | 300 W | 70 W | 4.3x higher on A100 |
| Released | Q2 2020 | Q3 2020 | |
| Precision | |||
| Supported formats | FP16BF16TF32FP32FP64INT4INT8 | FP16FP32INT4INT8 | |
Figures are for each model's headline configuration. Where a form factor carries a different number, it is named under the figure.
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: A100 datasheet and T4G datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | A100 /GPU/hr | T4G /GPU/hr |
|---|---|---|
GPU.ai
|
On-Demand $0.89 | -- |
Thunder Compute
|
On-Demand $1.09 | -- |
Massed Compute
|
On-Demand $1.35 | -- |
Packet·ai
|
On-Demand $1.43 | -- |
Spheron
|
On-Demand $1.43 | -- |
Oblivus
|
On-Demand $1.47 | -- |
Sesterce
|
On-Demand $1.49 | -- |
Geodd
|
On-Demand $1.49 | -- |
AWS
|
-- | On-Demand $0.42 |
43 providers list the A100 and 1 the T4G. Every listing is on the A100 page and the T4G page.
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia A100 was last updated on Sept. 7, 2026, and for Nvidia T4G on Sept. 7, 2026.