consumer
租用 Nvidia GeForce GTX 1660 Super.
Turing
6GB VRAM
From $0.027/hr
Per hour
$0.027
Per day
$0.64
Per week
$4.47
Per month
$19
Provider spread
2 providers ·
up to 63% cheaper at the low end
Cheapest · $0.027/hr on Clore.ai
Median $0.049/hr
Most expensive · $0.072/hr on Theta EdgeCloud
Price history
Daily median across providers.
Loading...
Where to rent it
All providers carrying this GPU.
AI models that fit
See all 91 →
Run these on this GPU.
- Gemma 2 9B 1× · int4
- Gemma 2 9B It 1× · int4
- Moondream 1.8B 1× · fp16
Cloud instances
See all 19 →
Hyperscaler bundles.
Pre-configured on 1 clouds — from $0.06/hr total
($0.065/hr per GPU).
FAQ
Frequently asked.
How much does it cost to rent the Nvidia GeForce GTX 1660 Super right now?
The cheapest current listing is $0.027/hr on Clore.ai, and the median across the 2 providers listing it is $0.072/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $19.
What AI models can the Nvidia GeForce GTX 1660 Super run?
Its memory is too small for current LLMs beyond very small models; it's better suited to lightweight inference such as embeddings or small vision models.
Which models are recommended for the Nvidia GeForce GTX 1660 Super?
91 models in our catalog have a recommended configuration for this card, with the quantization that fits its 6 GB — see the AI models tab.
Why does the Nvidia GeForce GTX 1660 Super cost different amounts on different providers?
Marketplaces such as Vast.ai and Clore.ai list machines from independent hosts who set their own prices, so competition pushes rates down but reliability varies by host. Operator clouds such as Lambda and the hyperscalers charge more for consistent hardware, support and networking. Prices here are per GPU, so they compare directly.
How is the Nvidia GeForce GTX 1660 Super price calculated?
We collect listings from each provider's public API or price page — every 5–10 minutes for marketplaces, up to daily for operator clouds — and show the median hourly price per provider from the last 24 hours, so one unusually cheap listing doesn't set the headline. Details are on the methodology page.
Cloud instance options
Pre-configured instances on hyperscalers.
Whole-instance bundles (GPU + vCPU + RAM + disk) on the major clouds. Per-GPU rate often drops as the count rises. View = spec page · Launch = sign up (affiliate).
Cheapest bundle
$0.06/hr
Lowest $/hr per GPU
$0.065/hr
Providers
1
Instance shapes
19
| Provider | Instance | GPUs | vCPU | RAM | Disk | $/hr | $/hr per GPU | |
|---|---|---|---|---|---|---|---|---|
| community-1x | 1× | — | — | — | $0.06/hr | $0.065/hr | ||
| community-1x | 1× | — | — | — | $0.06/hr | $0.065/hr | ||
| community-1x | 1× | — | — | — | $0.06/hr | $0.065/hr | ||
| community-1x | 1× | — | — | — | $0.06/hr | $0.065/hr | ||
| community-1x | 1× | — | — | — | $0.07/hr | $0.072/hr | ||
| community-1x | 1× | — | — | — | $0.07/hr | $0.072/hr | ||
| community-1x | 1× | — | — | — | $0.07/hr | $0.072/hr | ||
| community-1x | 1× | — | — | — | $0.07/hr | $0.072/hr | ||
| community-1x | 1× | — | — | — | $0.07/hr | $0.072/hr | ||
| community-1x | 1× | — | — | — | $0.07/hr | $0.072/hr | ||
| community-1x | 1× | — | — | — | $0.07/hr | $0.072/hr | ||
| community-1x | 1× | — | — | — | $0.07/hr | $0.072/hr | ||
| community-1x | 1× | — | — | — | $0.07/hr | $0.072/hr | ||
| community-1x | 1× | — | — | — | $0.07/hr | $0.072/hr | ||
| community-1x | 1× | — | — | — | $0.07/hr | $0.072/hr | ||
| community-1x | 1× | — | — | — | $0.07/hr | $0.072/hr | ||
| community-1x | 1× | — | — | — | $0.07/hr | $0.072/hr | ||
| community-1x | 1× | — | — | — | $0.07/hr | $0.072/hr | ||
| community-1x | 1× | — | — | — | $0.08/hr | $0.078/hr |
Looking for the cheapest rate?
Hyperscaler bundles include managed networking + SLAs. Raw per-GPU rental on P2P marketplaces is typically 3–10× cheaper.
See raw rental rates on the Overview tab →
FAQ
Cloud instances — common questions.
How much does it cost to rent the Nvidia GeForce GTX 1660 Super right now?
The cheapest current listing is $0.027/hr on Clore.ai, and the median across the 2 providers listing it is $0.072/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $19.
What AI models can the Nvidia GeForce GTX 1660 Super run?
Its memory is too small for current LLMs beyond very small models; it's better suited to lightweight inference such as embeddings or small vision models.
Which models are recommended for the Nvidia GeForce GTX 1660 Super?
91 models in our catalog have a recommended configuration for this card, with the quantization that fits its 6 GB — see the AI models tab.
Why does the Nvidia GeForce GTX 1660 Super cost different amounts on different providers?
Marketplaces such as Vast.ai and Clore.ai list machines from independent hosts who set their own prices, so competition pushes rates down but reliability varies by host. Operator clouds such as Lambda and the hyperscalers charge more for consistent hardware, support and networking. Prices here are per GPU, so they compare directly.
How is the Nvidia GeForce GTX 1660 Super price calculated?
We collect listings from each provider's public API or price page — every 5–10 minutes for marketplaces, up to daily for operator clouds — and show the median hourly price per provider from the last 24 hours, so one unusually cheap listing doesn't set the headline. Details are on the methodology page.
AI models
INT4
INT4
FP16
FP16
FP16
FP16
INT4
INT4
INT4
INT4
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
FP8
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
INT4
Models that run on this GPU.
GPU-count + quantization recommendations covering fine-tuning, inference, and run-it-yourself scenarios on the Nvidia GeForce GTX 1660 Super.
Gemma 2 9B
by Google DeepMind
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
9B
Context
8K tokens
Gemma 2 9B It
by Google DeepMind
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
9B
Context
8K tokens
Moondream 1.8B
by Moondream
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
2B
Context
2K tokens
Gemma 2B It
by Google DeepMind
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
2B
Context
8K tokens
Qwen3.5-2B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
2B
Context
262K tokens
Qwen3.5 2B Lora
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
2B
Context
262K tokens
Nvidia Nemotron Nano 9B V2
by Nvidia
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
9B
Context
131K tokens
GLM-4.7
by Zhipu AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
9B
Context
203K tokens
Qwen: Qwen3.5-9B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
9B
Context
262K tokens
Qwen3.5 9B Fp8
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
9B
Context
262K tokens
Stable Diffusion XL
by Stability AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
4B
Llama 3.2 3B
by Meta AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
3B
Context
128K tokens
Qwen 3 4B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
4B
Context
33K tokens
Gemma 3 4B
by Google DeepMind
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
4B
Context
128K tokens
Phi-3.5 Mini
by Microsoft
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
4B
Context
128K tokens
Phi-3 Mini
by Microsoft
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
4B
Context
128K tokens
Microsoft: Phi 4 Mini Instruct
by Microsoft
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
4B
Context
131K tokens
Qwen3 4B Base
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
4B
Context
33K tokens
Gemma 3 4b it
by Google DeepMind
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
4B
Context
66K tokens
Qwen3 4B Instruct 2507
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
4B
Context
262K tokens
Qwen3.5-4B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
4B
Context
262K tokens
Qwen3.5 4B Lora
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
4B
Context
262K tokens
DeepSeek R1 Distill Qwen 7B
by DeepSeek
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
128K tokens
Stable Diffusion 3.5 Large
by Stability AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Llama 3.1 8B
by Meta AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
128K tokens
Mistral 7B v0.3
by Mistral AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
33K tokens
Mistral 7B v0.2
by Mistral AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
33K tokens
Mistral 7B v0.1
by Mistral AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
8K tokens
Qwen 2.5 7B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
128K tokens
Qwen 3 8B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
128K tokens
LLaVA 7B
by LLaVA Project
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
4K tokens
Code Llama 7B
by Meta AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
16K tokens
DeepSeek Coder 6.7B
by DeepSeek
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
16K tokens
OLMo 3 7B
by Allen Institute for AI (AI2)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
4K tokens
OLMo 7B
by Allen Institute for AI (AI2)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
2K tokens
?
INT4
Hermes 3 8B
by Nous Research
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
128K tokens
IBM Granite 3.1 8B
by IBM Research
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
128K tokens
IBM Granite Code 8B
by IBM Research
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
4K tokens
IBM: Granite 4.1 8B
by IBM Research
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
131K tokens
Reka Edge
by Rekaai
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
16K tokens
Xiaomi: MiMo-V2-Flash
by Xiaomi
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
262K tokens
Mistral: Ministral 3 8B 2512
by Mistral AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
262K tokens
Qwen: Qwen3 VL 8B Thinking
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
256K tokens
Qwen: Qwen3 VL 8B Instruct
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
256K tokens
NVIDIA: Nemotron Nano 9B V2
by Nvidia
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
9B
Context
131K tokens
Z.ai: GLM 4.5V
by Zhipu AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
9B
Context
66K tokens
?
INT4
ByteDance: UI-TARS 7B
by Bytedance
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
128K tokens
?
INT4
Morph: Morph V3 Fast
by Morph
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
82K tokens
Qwen: Qwen3 8B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
131K tokens
?
INT4
AlfredPros: CodeLLaMa 7B Instruct Solidity
by Alfredpros
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
4K tokens
Llama Guard 3 8B
by Meta AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
131K tokens
?
INT4
AionLabs: Aion-RP 1.0 (8B)
by Aion Labs
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
33K tokens
Qwen: Qwen2.5 7B Instruct
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
131K tokens
?
INT4
Sao10K: Llama 3 8B Lunaris
by Sao10k
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
8K tokens
?
INT4
NousResearch: Hermes 2 Pro - Llama-3 8B
by Nous Research
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
8K tokens
Meta: Llama 3 8B Instruct
by Meta AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
8K tokens
Mistral: Mistral 7B Instruct v0.1
by Mistral AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
4K tokens
Qwen2.5 7B Instruct Turbo
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
33K tokens
Meta Llama 3 8B Instruct Lite
by Meta AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
8K tokens
?
INT4
Nous Hermes 2 Mixtral 8X7B Dpo
by Nous Research
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
33K tokens
nim/meta/llama-3.1-8b-instruct
by Meta AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
16K tokens
Cogito V1 Preview Llama 8B
by Deepcogito
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
131K tokens
Mixtral 8x7B Instruct V0.1 FP8 Lora
by Mistral AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
33K tokens
Qwen 2 (7B)
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
33K tokens
Qwen2.5 7B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
131K tokens
Qwen2.5 7B Instruct
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
33K tokens
Qwen3 1.7B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
41K tokens
Qwen3 1.7B Base
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
33K tokens
Qwen3 8B Base
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
33K tokens
meta-llama/Llama-2-7b-chat-hf
by Meta AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
4K tokens
Qwen3 8B Lora
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
41K tokens
Meta Llama 3.1 8B Instruct Awq Int4
by Meta AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
131K tokens
Meta Llama 3.1 8B Instruct Turbo
by Meta AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
131K tokens
Meta Llama 3 8B Instruct
by Meta AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
8K tokens
Mistral (7B) Instruct v0.3
by Mistral AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
33K tokens
Mixtral 8X7b V0.1
by Mistral AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
33K tokens
nim/mistralai/mixtral-8x7b-instruct-v01
by Mistral AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
16K tokens
Mixtral-8x7B Instruct v0.1
by Mistral AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
33K tokens
Meta Llama 3.1 8B
by Meta AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
16K tokens
Molmo 7B D 0924
by Allen Institute for AI (AI2)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
4K tokens
Meta Llama 3 8B Instruct Reference
by Meta AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
8K tokens
Qwen3.5-0.8B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
262K tokens
?
INT4
L3-8B-Lunaris-v1-Turbo
by Sao10k
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
8K tokens
Meta-Llama-3.1-8B-Instruct
by Meta AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
131K tokens
Qwen3.5 0.8B Lora
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
262K tokens
Qwen3.5 9B Lora
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
9B
Context
262K tokens
?
INT4
LFM2.5-8B-A1B
by LiquidAI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
128K tokens
Tencent: Hy-MT2-1.8B
by Tencent
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
8K tokens
Mistral: Ministral 8B
by Mistral AI
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
8B
Context
128K tokens
Tencent: Hy-MT2-7B
by Tencent
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
7B
Context
8K tokens
granite-4.2-8b
by IBM Research
Required GPUs
1× Nvidia GeForce GTX 1660 Super
Total VRAM
6 GB
Parameters
9B
Context
131K tokens
Renting for inference?
Pair these models with the cheapest provider on the rental table.
See rental rates on the Overview tab →
FAQ
AI models on this GPU.
How much does it cost to rent the Nvidia GeForce GTX 1660 Super right now?
The cheapest current listing is $0.027/hr on Clore.ai, and the median across the 2 providers listing it is $0.072/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $19.
What AI models can the Nvidia GeForce GTX 1660 Super run?
Its memory is too small for current LLMs beyond very small models; it's better suited to lightweight inference such as embeddings or small vision models.
Which models are recommended for the Nvidia GeForce GTX 1660 Super?
91 models in our catalog have a recommended configuration for this card, with the quantization that fits its 6 GB — see the AI models tab.
Why does the Nvidia GeForce GTX 1660 Super cost different amounts on different providers?
Marketplaces such as Vast.ai and Clore.ai list machines from independent hosts who set their own prices, so competition pushes rates down but reliability varies by host. Operator clouds such as Lambda and the hyperscalers charge more for consistent hardware, support and networking. Prices here are per GPU, so they compare directly.
How is the Nvidia GeForce GTX 1660 Super price calculated?
We collect listings from each provider's public API or price page — every 5–10 minutes for marketplaces, up to daily for operator clouds — and show the median hourly price per provider from the last 24 hours, so one unusually cheap listing doesn't set the headline. Details are on the methodology page.