consumer
Louer Nvidia GeForce RTX 3090.
Ampere
24GB VRAM
350W
2020
From $0.12/hr
Per hour
$0.12
Per day
$2.91
Per week
$20.34
Per month
$87
Provider spread
8 providers ·
up to 55% cheaper at the low end
Cheapest · $0.12/hr on Vast.ai
Median $0.20/hr
Most expensive · $0.27/hr on io.net
Price history
Daily median across providers.
Loading...
Where to rent it
All providers carrying this GPU.
Buy vs rent
Should you rent or own?
Your usage
Rent on cloud
Per day
—
Per month
—
at $0.12/hr cheapest provider rate
Own on-prem
Electricity per day
—
350W TDP
Workloads
Suitable workloads.
AI models that fit
See all 34 →
Run these on this GPU.
- Stable Diffusion XL 1× · fp16
- Mistral 7B v0.2 1× · fp16
- Mistral 7B v0.1 1× · fp16
Cloud instances
See all 24 →
Hyperscaler bundles.
Pre-configured on 1 clouds — from $0.19/hr total
($0.082/hr per GPU).
FAQ
Frequently asked.
How much does it cost to rent the Nvidia GeForce RTX 3090 right now?
The cheapest current listing is $0.12/hr on Vast.ai, and the median across the 8 providers listing it is $0.21/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $88.
What AI models can the Nvidia GeForce RTX 3090 run?
With 24 GB it runs 7–8B models at FP16, 13–14B at INT8 and about 32B at 4-bit. A 70B model needs a 48 GB card or two 24 GB cards. It can QLoRA fine-tune 7–14B models.
Which models are recommended for the Nvidia GeForce RTX 3090?
34 models in our catalog have a recommended configuration for this card, with the quantization that fits its 24 GB — see the AI models tab.
Why does the Nvidia GeForce RTX 3090 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 RTX 3090 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
$0.19/hr
Lowest $/hr per GPU
$0.082/hr
Providers
1
Instance shapes
24
| Provider | Instance | GPUs | vCPU | RAM | Disk | $/hr | $/hr per GPU | |
|---|---|---|---|---|---|---|---|---|
| community-1x | 1× | — | — | — | $0.19/hr | $0.19/hr | ||
| community-1x | 1× | — | — | — | $0.19/hr | $0.19/hr | ||
| community-1x | 1× | — | — | — | $0.19/hr | $0.19/hr | ||
| community-1x | 1× | — | — | — | $0.19/hr | $0.19/hr | ||
| community-1x | 1× | — | — | — | $0.19/hr | $0.19/hr | ||
| community-1x | 1× | — | — | — | $0.19/hr | $0.19/hr | ||
| community-1x | 1× | — | — | — | $0.21/hr | $0.21/hr | ||
| community-1x | 1× | — | — | — | $0.22/hr | $0.22/hr | ||
| community-1x | 1× | — | — | — | $0.22/hr | $0.22/hr | ||
| community-1x | 1× | — | — | — | $0.22/hr | $0.22/hr | ||
| community-1x | 1× | — | — | — | $0.22/hr | $0.22/hr | ||
| community-1x | 1× | — | — | — | $0.22/hr | $0.22/hr | ||
| community-1x | 1× | — | — | — | $0.22/hr | $0.22/hr | ||
| community-1x | 1× | — | — | — | $0.22/hr | $0.22/hr | ||
| community-1x | 1× | — | — | — | $0.22/hr | $0.22/hr | ||
| community-1x | 1× | — | — | — | $0.22/hr | $0.22/hr | ||
| community-1x | 1× | — | — | — | $0.22/hr | $0.22/hr | ||
| community-1x | 1× | — | — | — | $0.22/hr | $0.22/hr | ||
| community-1x | 1× | — | — | — | $0.22/hr | $0.22/hr | ||
| community-3x | 3× | — | — | — | $0.25/hr | $0.082/hr | ||
| community-3x | 3× | — | — | — | $0.25/hr | $0.082/hr | ||
| community-3x | 3× | — | — | — | $0.25/hr | $0.082/hr | ||
| community-3x | 3× | — | — | — | $0.25/hr | $0.082/hr | ||
| community-3x | 3× | — | — | — | $0.25/hr | $0.082/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 RTX 3090 right now?
The cheapest current listing is $0.12/hr on Vast.ai, and the median across the 8 providers listing it is $0.21/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $88.
What AI models can the Nvidia GeForce RTX 3090 run?
With 24 GB it runs 7–8B models at FP16, 13–14B at INT8 and about 32B at 4-bit. A 70B model needs a 48 GB card or two 24 GB cards. It can QLoRA fine-tune 7–14B models.
Which models are recommended for the Nvidia GeForce RTX 3090?
34 models in our catalog have a recommended configuration for this card, with the quantization that fits its 24 GB — see the AI models tab.
Why does the Nvidia GeForce RTX 3090 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 RTX 3090 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
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
FP16
INT4
FP16
INT4
INT8
INT4
INT4
FP8
FP8
FP8
FP8
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 RTX 3090.
Stable Diffusion XL
by Stability AI
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
4B
The most-deployed image-gen GPU pair.
Mistral 7B v0.2
by Mistral AI
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
7B
Context
33K tokens
Mistral 7B v0.1
by Mistral AI
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
7B
Context
8K tokens
Historical baseline.
?
INT4
TheDrummer: Skyfall 36B V2
by Thedrummer
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
36B
Context
33K tokens
Mistral 7B v0.3
by Mistral AI
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
7B
Context
33K tokens
Stable Diffusion 3.5 Large
by Stability AI
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
8B
Qwen 3 8B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
8B
Context
128K tokens
Gemma 2 9B
by Google DeepMind
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
9B
Context
8K tokens
GLM-4.7
by Zhipu AI
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
9B
Context
203K tokens
Qwen: Qwen3.5-9B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
9B
Context
262K tokens
NVIDIA: Nemotron Nano 9B V2
by Nvidia
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
9B
Context
131K tokens
Z.ai: GLM 4.5V
by Zhipu AI
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
9B
Context
66K tokens
Gemma 2 9B It
by Google DeepMind
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
9B
Context
8K tokens
Nvidia Nemotron Nano 9B V2
by Nvidia
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
9B
Context
131K tokens
Qwen3.5 9B Fp8
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
9B
Context
262K tokens
Qwen3.6 35B A3b Fp8
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
35B
Context
262K tokens
Stable Diffusion 3.5 Medium
by Stability AI
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
3B
Qwen: Qwen3.5-35B-A3B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
35B
Context
262K tokens
DeepSeek R1 Distill Qwen 14B
by DeepSeek
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
15B
Context
128K tokens
Qwen: Qwen3.6 35B A3B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
35B
Context
262K tokens
?
INT4
Holo3 35B A3b
by Hcompany
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
35B
Context
262K tokens
LLaVA 34B
by LLaVA Project
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
34B
Context
4K tokens
Llama 4 Scout 17B 16E Instruct Fp8 Lora
by Meta AI
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
17B
Context
10.5M tokens
Llama 4 Maverick Instruct (17Bx128E) FP8
by Meta AI
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
17B
Context
1M tokens
Llama 4 Scout (17Bx16E)
by Meta AI
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
17B
Context
262K tokens
Llama 4 Scout Instruct (17Bx16E)
by Meta AI
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
17B
Context
1M tokens
Qwen 2.5 Coder 32B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
33B
Context
128K tokens
DeepSeek R1 Distill Qwen 32B
by DeepSeek
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
33B
Context
128K tokens
Qwen 2.5 32B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
33B
Context
128K tokens
Qwen 3 32B
by Alibaba (Qwen Team)
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
33B
Context
128K tokens
Code Llama 34B
by Meta AI
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
34B
Context
16K tokens
DeepSeek Coder 33B
by DeepSeek
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
33B
Context
16K tokens
Yi-34B
by 01.AI
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
34B
Context
32K tokens
Deepseek Coder 33B Instruct
by DeepSeek
Required GPUs
1× Nvidia GeForce RTX 3090
Total VRAM
24 GB
Parameters
33B
Context
16K 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 RTX 3090 right now?
The cheapest current listing is $0.12/hr on Vast.ai, and the median across the 8 providers listing it is $0.21/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $88.
What AI models can the Nvidia GeForce RTX 3090 run?
With 24 GB it runs 7–8B models at FP16, 13–14B at INT8 and about 32B at 4-bit. A 70B model needs a 48 GB card or two 24 GB cards. It can QLoRA fine-tune 7–14B models.
Which models are recommended for the Nvidia GeForce RTX 3090?
34 models in our catalog have a recommended configuration for this card, with the quantization that fits its 24 GB — see the AI models tab.
Why does the Nvidia GeForce RTX 3090 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 RTX 3090 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.