Is the GTX 1660 Ti suitable for AI training?

Only small models. It has no Tensor Cores and 6 GB of memory, so training modern networks is slow and memory-limited. An RTX 3060 with 12 GB is a better training starter.

GTX 1660 Ti vs RTX A2000?

Both have 6 GB. The RTX A2000 is Ampere with about 11.2 TFLOPS FP32 and BF16 support, around twice the GTX 1660 Ti's 5.3 TFLOPS.

Which LLMs fit in 6 GB?

3B–4B models at 4-bit run comfortably; 7B models at 4-bit are tight and need a short context. For 7B–8B models at 8-bit, choose 12 GB or more.

Can I stop the server and resume later on Cloudj?

Yes. A stopped instance keeps its disk and is charged for storage only. Stopping releases the GPU, so starting again may wait until it is free. Destroy it when you no longer need the data.

GPU Cloud · NVIDIA · Turing

Rent an NVIDIA GTX 1660 Ti GPU with 6 GB VRAM

Rent GTX 1660 Ti cloud GPU servers by the hour on Cloudj: 6 GB VRAM, NVIDIA Turing and about 5.3 TFLOPS FP32 at a 120 W power limit. It suits students and developers who want a cheap-class Turing GPU for coding practice, small vision models and quantized LLM experiments. Pick a live configuration, start from the Ubuntu 22.04 + CUDA or PyTorch + JupyterLab template and connect over SSH with your key.

Rent GTX 1660 Ti All GPUs

GTX 1660 Ti specifications

VRAM per GPU

6 GB

Architecture

NVIDIA Turing

Compute capability

7.5

FP32 compute

≈ 5.3 TFLOPS

Memory bandwidth

≈ 234 GB/s

Power limit

120 W

Values reported by the infrastructure provider for machines currently listed; real performance varies by machine.

Live GTX 1660 Ti configurations and prices

Out of stock right now

Browse available GPUs

What you can run on the GTX 1660 Ti cloud GPU

Small model inference

Run compact vision and text models, and 3B-class LLMs at 4-bit, in 6 GB.

CUDA code testing

Compile and test CUDA kernels on compute capability 7.5 before deploying on RTX or datacenter GPUs.

Notebook-based learning

Work through ML tutorials and course notebooks on a dedicated GPU.

Light video and image jobs

Speed up small batch image transforms and GPU-accelerated scripts.

Is the GTX 1660 Ti the right GPU for your workload?

Choose the GTX 1660 Ti for code verification, learning, and lightweight inference workloads that fit into 6 GB of consumer-grade memory. Select a GPU with more VRAM and higher bandwidth for model fine-tuning, large language model serving, or high-resolution media generation, or opt for a smaller GPU only if your workload requires minimal graphical or compute acceleration.

GTX 1660 Ti vs similar cloud GPUs

GPU	VRAM per GPU	FP32 compute	Power limit
NVIDIA GTX 1660 Ti	6 GB	≈ 5.3 TFLOPS	120 W
NVIDIA GTX 1070 Ti	8 GB	≈ 7.4 TFLOPS	180 W	Details →
NVIDIA GTX 1080	8 GB	≈ 7.8 TFLOPS	130 W	Details →
NVIDIA GTX 1080 Ti	11 GB	≈ 11 TFLOPS	250 W	Details →
NVIDIA GTX 1650	4 GB	≈ undefined TFLOPS	W	Details →

Guides for GTX 1660 Ti

GPU cloud Asia guide: Japan, Singapore, Korea and nearbyA practical GPU cloud Asia guide: which country codes to search for East and Southeast Asian users, a fallback order, and how to pair a GPU with a VPS.GPU cloud by location: how to pick a country for your GPUHow GPU cloud by location works on Cloudj: filter a live list of machines by country code, decide between near users, lowest price or data rules.GPU cloud Europe: choosing a country for your AI workloadsA practical guide to GPU cloud Europe searches: filter by several country codes at once, weigh Western, Nordic and Eastern hosts, and plan where data lives.GPU cloud North America: renting GPUs in the US and CanadaA GPU cloud North America guide: how to search US and CA hosts, read the results, pick a VPS front end and decide when a US GPU suits users elsewhere.

All articles →

GTX 1660 Ti cloud GPU: frequently asked questions

Rent the GTX 1660 Ti cloud GPU by the hour

Pick a live configuration, choose a template and connect over SSH with your key. Billing stops when you destroy the instance.

Rent GTX 1660 Ti All GPUs