A workstation GPU against a data center card, one Maxwell and one Turing: 2 GB DDR3 against 16 GB GDDR6 and 11x the memory bandwidth on the T4G.
At a glance
Updated 12 hours ago- Memory
- 2 GB
- DDR3
- Memory bandwidth
- 29 GB/s
- From
- --
- 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 | K620 | T4G | Difference |
|---|---|---|---|
| On-demand | -- | $0.42 | |
| Reserved | No reserved listings | $0.18 | |
| Median | -- | $1.10 |
Median: Median across providers, one vote each, so a large catalog does not outweigh a small one.
Price history
K620 vs T4G price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | K620 | T4G | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 2 GB DDR3 | 16 GB GDDR6 | 8x more on T4G |
| Bandwidth | 29 GB/s | 320 GB/s | 11x higher on T4G |
| Bus width | 128-bit | 256-bit | 2x wider on T4G |
| Compute · dense | |||
| FP16 / BF16 | Not supported | 65 TFLOPS | T4G only |
| INT8 | Not supported | 130 TOPS | T4G only |
| FP32 | 0.9 TFLOPS | 8.1 TFLOPS | 9.4x higher on T4G |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 45 W | 70 W | 1.6x higher on T4G |
| Released | Q3 2014 | Q3 2020 | 6 years newer on T4G |
| Precision | |||
| Supported formats | FP32 | FP16FP32INT4INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: K620 datasheet and T4G datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | K620 /GPU/hr | T4G /GPU/hr |
|---|---|---|
AWS
|
-- | On-Demand $0.42 |
Similar GPUs
Other comparisons in the same class.
Our data for Nvidia K620 was last updated on Sept. 7, 2026, and for Nvidia T4G on Sept. 7, 2026.