NVIDIA GTX 1660 Ti

6 GB VRAM120 W TDP2 providers3 offerings3 regions

The NVIDIA GTX 1660 Ti is a consumer-grade GPU built on the Turing architecture, featuring 6 GB of memory with 288 GB/s of memory bandwidth and a 120 W TDP. It delivers 5.4 TFLOPS of FP32 performance. Currently available from 2 providers starting at $0.10/GPU/hour, with a market median of $0.61/GPU/hour across 3 configurations.

Cheapest

$0.100/hr

Theta EdgeCloud

Median

$0.610/hr

across 3 offerings

Most expensive

$1.340/hr

Vast.ai

90-day trend

+771.4%

median rate

Hardware specifications

Same across all providers

Memory

6 GB

What LLMs fit? ↓

TDP

120 W

Memory bandwidth

288 GB/s

Architecture

Turing

FP32 performance

5.4 TFLOPS

Brand

NVIDIA

Series

GeForce GTX

Market price history

Median price across all providers

Prices updated 3 hours ago

2 offerings from 2 providers

Sorted by price ascending. Compare configurations side-by-side.

Provider	Count	vCPU	RAM	Per GPU hour	Total/hr	Action
Vast.aiPromoted Affiliate promotion — we may earn a commission.	×1	4	8 GB	$0.610	$0.61	Launch
Theta EdgeCloudTrendingCheapest	×1	8	29 GB	$0.100 0.0% 30d	$0.10	Launch
Vast.aiReferral linkTrending	×1	4	8 GB	From$0.610 +195.5% 30d	From$0.61	Launch

LLMs that fit on the NVIDIA GTX 1660 Ti

Estimated VRAM for popular open-weight LLMs at 16-bit (FP16/BF16), 8-bit (FP8/INT8) and 4-bit (INT4/MXFP4) precision, against 6 GB per GPU.

Model	Parameters	16-bit	8-bit	4-bit
Granite 4.1 8B IBM	8.8B	21 GB Too large	12 GB Too large	6.8 GB Tight on 1× · 6% spare
Qwen3 8B Alibaba	8.2B	20 GB Too large	11 GB Too large	6.3 GB Tight on 1× · 14% spare
Llama 3.1 8B Instruct Meta	8B	19 GB Too large	11 GB Too large	6.2 GB Tight on 1× · 16% spare
Mistral 7B Instruct v0.3 Mistral AI	7.2B	17 GB Too large	9.6 GB Too large	5.6 GB Barely fits on 1×
Qwen3 4B Alibaba	4B	9.7 GB Too large	5.3 GB Barely fits on 1×	3.1 GB 1× · 2.9 GB free

Estimates: model weights plus 20% for KV cache and runtime overhead, at short context lengths. Long contexts and large batches need more. Rows marked “tight” hold the weights but not that full margin. A ×N figure is the total VRAM across N of these GPUs and makes no claim about interconnect throughput. How we estimate this · Start from a model instead

Want more from this page?

See incorrect data?

Frequently asked questions

How much does the GTX 1660 Ti cost per hour?

The GTX 1660 Ti starts at $0.10 per GPU-hour, with a median of $0.61 across 3 available configurations. Actual pricing depends on the provider, region, and whether you rent on-demand, spot or reserved.

Which cloud providers offer the GTX 1660 Ti?

2 providers currently list the GTX 1660 Ti: Vast.ai, Theta EdgeCloud. Compare their hourly pricing, regions and machine specs in the table above.

How much VRAM does the GTX 1660 Ti have?

The GTX 1660 Ti comes with 6 GB of VRAM, which determines the largest models and batch sizes it can hold in memory for training and inference.

Which LLMs can I run on the GTX 1660 Ti?

With 6 GB of VRAM, a single GTX 1660 Ti can serve models such as Mistral 7B Instruct v0.3, Qwen3 4B. The table above lists the estimated VRAM for each model at 16-bit, 8-bit and 4-bit precision, including the multi-GPU configurations needed for larger models.

Where is the GTX 1660 Ti cheapest?

The lowest on-demand price we currently track for the GTX 1660 Ti is $0.10 per GPU-hour at Theta EdgeCloud. Because providers update pricing and availability frequently, check the live table above before you launch.