Two Nvidia data center GPUs, one Turing and one Volta: 16 GB GDDR6 against 32 GB HBM2, 3.5x the memory bandwidth on the V100S, and NVLink 300 GB/s on the V100S where the T4G is PCIe only.
At a glance
Memory
- T4G
- 16 GB
- V100S
- 32 GB
2x more on V100S
Memory bandwidth
- T4G
- 320 GB/s
- V100S
- 1,134 GB/s
3.5x higher on V100S
Cheapest on-demand
- T4G
- $0.42 /GPU/hr
- V100S
- $0.88 /GPU/hr
2.1x more expensive on V100S
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | T4G | V100S | Difference |
|---|---|---|---|
| On-demand | -- /GPU/hr from $0.42 | -- /GPU/hr from $0.88 | |
| Reserved | -- /GPU/hr from $0.18 (36 mo) | No reserved 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 and on-demand on the V100S: 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
T4G vs V100S price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | T4G | V100S | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 16 GB GDDR6 | 32 GB HBM2 | 2x more on V100S |
| Bandwidth | 320 GB/s | 1,134 GB/s | 3.5x higher on V100S |
| Bus width | 256-bit | 4,096-bit | 16x wider on V100S |
| Compute · dense | |||
| FP16 / BF16 | 65 TFLOPS | 130 TFLOPS | 2x higher on V100S |
| INT8 | 130 TOPS | ||
| FP32 | 8.1 TFLOPS | 16.4 TFLOPS | 2x higher on V100S |
| FP64 | Not supported | 8.2 TFLOPS | V100S only |
| Platform | |||
| Interconnect | PCIe only | NVLink 300 GB/s | NVLink on V100S only |
| Board power | 70 W | 250 W | 3.6x higher on V100S |
| Released | Q3 2020 | Q4 2019 | 9 months newer on T4G |
| Precision | |||
| Supported formats | FP16FP32INT4INT8 | FP16FP32FP64INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: T4G datasheet and V100S datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | T4G /GPU/hr | V100S /GPU/hr |
|---|---|---|
AWS
|
On-Demand $0.42 | -- |
OVH
|
-- | On-Demand $0.88 |
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia T4G was last updated on Sept. 7, 2026, and for Nvidia V100S on Sept. 7, 2026.