Vast.ai Our sponsor
USA 3 configs 1x
You can start using a GTX 1660 for $0.04/hr per GPU (on-demand). It's a low-risk price point for smaller workloads compared to the market high of $0.68/hr. Spot instances start lower, at $0.04/hr per GPU.
USA 3 configs 1x
USA 1 config 1x
USA 4 configs 1x
Heads up: We do our best to keep these specs & prices accurate. However, cloud costs may fluctuate based on region, usage, and other factors not listed here. These are estimates based on common setups and are for informational purposes only. Always verify current rates & exact specs with the provider before provisioning.
6GB GDDR5. Budget Turing GPU without RT or Tensor Cores.
No Tensor Cores and only 6GB VRAM. Only viable for basic cloud desktop rendering or legacy compute tasks.
The median on-demand price across providers has fallen about 62% since August 2025, from $0.14 to $0.05/hr per GPU. This reflects the market-wide median, which moves both when providers change prices and when lower or higher priced offerings enter the market.
With 6GB of VRAM, the GTX 1660 is mainly limited to small quantized models and lightweight GPU workloads.
The GTX 1660 has 6GB of VRAM. Multi-GPU setups increase total memory, but that memory is not automatically pooled across GPUs.
The GTX 1660 has 192 GB/s of memory bandwidth. Higher bandwidth helps with faster data transfer between GPU memory and compute cores.
The GTX 1660 supports 2 precision formats. Training: FP16, FP32.
No. The GTX 1660 is a PCIe-only GPU with no NVLink, so it is better suited to single-GPU inference and smaller-scale workloads than large distributed training jobs.
GTX 1660 pricing currently ranges from $0.04/hr to $0.68/hr per GPU, depending on the provider, instance type, and billing model.
At 720 hours per month, one GTX 1660 can cost between $27.22 to $488.02 per month, depending on the provider. Reserved and spot pricing can lower that further.
The GTX 1660 is available from 3 cloud providers: Salad, Database Mart, Vast.ai.
Yes. We currently track 8 GTX 1660 listings across 3 cloud providers:
| Billing type | Listings | Avg $/GPU/hr |
|---|---|---|
| On-demand | 2 | $0.36/hr |
| Reserved | 5 | $0.30/hr |
| Spot | 1 | $0.04/hr |
| Feature | Specification |
|---|---|
| GPU Microarchitecture | Turing |
| CUDA Cores | 1,408 |
| Memory | 6GB GDDR5 |
| FP16 (float) performance | 10 TFLOPS |
| FP32 (float) performance | 5 TFLOPS |
| FP64 (double) performance | 157 GFLOPS |
| Microsoft DirectX API | 12 |
| Vulkan RT API Support | Yes |
| OpenGL Support | Yes (4.6) |
Source: official Nvidia GTX 1660 datasheet.
Last updated