Two Nvidia consumer GPUs, one Turing and one Blackwell: 6 GB GDDR5 against 8 GB GDDR7 and 2.3x the memory bandwidth on the RTX 5060.
At a glance
Memory
- GTX 1660
- 6 GB
- RTX 5060
- 8 GB
1.3x more on RTX 5060
Memory bandwidth
- GTX 1660
- 192 GB/s
- RTX 5060
- 448 GB/s
2.3x higher on RTX 5060
Cheapest on-demand
- GTX 1660
- $0.04 /GPU/hr
- RTX 5060
- $0.10 /GPU/hr
2.6x more expensive on RTX 5060
Price comparison
Median price per GPU per hour by billing type, with the cheapest listing under it.
| Billing | GTX 1660 | RTX 5060 | Difference |
|---|---|---|---|
| On-demand | -- /GPU/hr from $0.04 | -- /GPU/hr from $0.10 | |
| Reserved | -- /GPU/hr from $0.19 (24 mo) | -- /GPU/hr from $0.12 (24 mo) | |
| Spot | -- /GPU/hr from $0.02 | -- /GPU/hr from $0.07 |
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, reserved and spot on the GTX 1660 and on-demand, reserved and spot on the RTX 5060: 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
GTX 1660 vs RTX 5060 price history
Weekly median on-demand price per GPU per hour
Specs comparison
| Spec | GTX 1660 | RTX 5060 | Difference |
|---|---|---|---|
| Memory | |||
| Capacity | 6 GB GDDR5 | 8 GB GDDR7 | 1.3x more on RTX 5060 |
| Bandwidth | 192 GB/s | 448 GB/s | 2.3x higher on RTX 5060 |
| Bus width | 192-bit | 128-bit | 1.5x wider on GTX 1660 |
| Compute · dense | |||
| FP4 | Not supported | 307 TFLOPS | RTX 5060 only |
| FP8 | Not supported | 76.8 TFLOPS | RTX 5060 only |
| FP16 / BF16 | 10.1 TFLOPS | 38.4 TFLOPS | 3.8x higher on RTX 5060 |
| INT8 | Not supported | 153.6 TOPS | RTX 5060 only |
| FP32 | 5.0 TFLOPS | 19.2 TFLOPS | 3.8x higher on RTX 5060 |
| Platform | |||
| Interconnect | PCIe only | PCIe only | |
| Board power | 120 W | 145 W | 1.2x higher on RTX 5060 |
| Released | Q1 2019 | Q2 2025 | 6 years newer on RTX 5060 |
| Precision | |||
| Supported formats | FP16FP32 | FP4FP8FP16BF16TF32FP32INT8 | |
Compute: Vendor peak figures, dense and per GPU. Not measured throughput.
Source: GTX 1660 datasheet and RTX 5060 datasheet.
Where to rent them
Providers listing these GPUs, those with both first, so you can switch without moving clouds.
| Provider | GTX 1660 /GPU/hr | RTX 5060 /GPU/hr |
|---|---|---|
Salad
|
On-Demand $0.0400 | On-Demand $0.11 |
Vast.ai
|
On-Demand $0.07 | On-Demand $0.10 |
Database Mart
|
Reserved (24mo) $0.19 | Reserved (24mo) $0.12 |
Similar GPUs
Other comparisons in the same class.
-
Nvidia RTX 3060
From $0.04 /GPU/hr Compare -
Nvidia RTX 2060
From $0.05 /GPU/hr Compare -
Nvidia GTX 1660 Super
From $0.04 /GPU/hr Compare -
Nvidia RTX 5060 Ti
From $0.09 /GPU/hr Compare -
Nvidia RTX 5070
From $0.16 /GPU/hr Compare
Our data for Nvidia GTX 1660 was last updated on Sept. 7, 2026, and for Nvidia RTX 5060 on Sept. 7, 2026.