consumer
Louer Nvidia RTX 4070 SUPER.
Ada Lovelace
12GB VRAM
From $0.18/hr
Per hour
$0.18
Per day
$4.30
Per week
$30.11
Per month
$129
Provider spread
2 providers ·
up to 8% cheaper at the low end
Cheapest · $0.18/hr on Clore.ai
Median $0.19/hr
Most expensive · $0.20/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 6 →
Run these on this GPU.
- Llama 4 Scout 17B 16E Instruct Fp8 Lora 1× · int4
- Llama 4 Scout Instruct (17Bx16E) 1× · int4
- Llama 4 Maverick Instruct (17Bx128E) FP8 1× · int4
Cloud instances
See all 21 →
Hyperscaler bundles.
Pre-configured on 1 clouds — from $0.20/hr total
($0.20/hr per GPU).
FAQ
Frequently asked.
How much does it cost to rent the Nvidia RTX 4070 SUPER right now?
The cheapest current listing is $0.18/hr on Clore.ai, and the median across the 2 providers listing it is $0.20/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $131.
What AI models can the Nvidia RTX 4070 SUPER run?
With 12 GB it's limited to small models: 7–8B at 4-bit, or 3–4B at higher precision, plus embedding and speech models. It's a budget option for experiments rather than serving.
Which models are recommended for the Nvidia RTX 4070 SUPER?
6 models in our catalog have a recommended configuration for this card, with the quantization that fits its 12 GB — see the AI models tab.
Why does the Nvidia RTX 4070 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 RTX 4070 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
$0.20/hr
Lowest $/hr per GPU
$0.20/hr
Providers
1
Instance shapes
21
| Provider | Instance | GPUs | vCPU | RAM | Disk | $/hr | $/hr per GPU | |
|---|---|---|---|---|---|---|---|---|
| community-1x | 1× | — | — | — | $0.20/hr | $0.20/hr | ||
| community-1x | 1× | — | — | — | $0.20/hr | $0.20/hr | ||
| community-1x | 1× | — | — | — | $0.20/hr | $0.20/hr | ||
| community-1x | 1× | — | — | — | $0.20/hr | $0.20/hr | ||
| community-1x | 1× | — | — | — | $0.20/hr | $0.20/hr | ||
| community-1x | 1× | — | — | — | $0.20/hr | $0.20/hr | ||
| community-1x | 1× | — | — | — | $0.20/hr | $0.20/hr | ||
| community-1x | 1× | — | — | — | $0.20/hr | $0.20/hr | ||
| community-1x | 1× | — | — | — | $0.20/hr | $0.20/hr | ||
| community-1x | 1× | — | — | — | $0.20/hr | $0.20/hr | ||
| community-1x | 1× | — | — | — | $0.20/hr | $0.20/hr | ||
| community-1x | 1× | — | — | — | $0.20/hr | $0.20/hr | ||
| community-1x | 1× | — | — | — | $0.20/hr | $0.20/hr | ||
| community-1x | 1× | — | — | — | $0.20/hr | $0.20/hr | ||
| community-1x | 1× | — | — | — | $0.20/hr | $0.20/hr | ||
| community-1x | 1× | — | — | — | $0.20/hr | $0.20/hr | ||
| community-1x | 1× | — | — | — | $0.20/hr | $0.20/hr | ||
| community-1x | 1× | — | — | — | $0.20/hr | $0.20/hr | ||
| community-1x | 1× | — | — | — | $0.20/hr | $0.20/hr | ||
| community-1x | 1× | — | — | — | $0.20/hr | $0.20/hr | ||
| community-1x | 1× | — | — | — | $0.20/hr | $0.20/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 RTX 4070 SUPER right now?
The cheapest current listing is $0.18/hr on Clore.ai, and the median across the 2 providers listing it is $0.20/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $131.
What AI models can the Nvidia RTX 4070 SUPER run?
With 12 GB it's limited to small models: 7–8B at 4-bit, or 3–4B at higher precision, plus embedding and speech models. It's a budget option for experiments rather than serving.
Which models are recommended for the Nvidia RTX 4070 SUPER?
6 models in our catalog have a recommended configuration for this card, with the quantization that fits its 12 GB — see the AI models tab.
Why does the Nvidia RTX 4070 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 RTX 4070 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
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 RTX 4070 SUPER.
Llama 4 Scout 17B 16E Instruct Fp8 Lora
by Meta AI
Required GPUs
1× Nvidia RTX 4070 SUPER
Total VRAM
12 GB
Parameters
17B
Context
10.5M tokens
Llama 4 Scout Instruct (17Bx16E)
by Meta AI
Required GPUs
1× Nvidia RTX 4070 SUPER
Total VRAM
12 GB
Parameters
17B
Context
1M tokens
Llama 4 Maverick Instruct (17Bx128E) FP8
by Meta AI
Required GPUs
1× Nvidia RTX 4070 SUPER
Total VRAM
12 GB
Parameters
17B
Context
1M tokens
Llama 4 Scout (17Bx16E)
by Meta AI
Required GPUs
1× Nvidia RTX 4070 SUPER
Total VRAM
12 GB
Parameters
17B
Context
262K tokens
DeepSeek Coder V2 Lite
by DeepSeek
Required GPUs
1× Nvidia RTX 4070 SUPER
Total VRAM
12 GB
Parameters
16B (2B active)
Context
128K tokens
DeepSeek R1 Distill Qwen 14B
by DeepSeek
Required GPUs
1× Nvidia RTX 4070 SUPER
Total VRAM
12 GB
Parameters
15B
Context
128K 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 RTX 4070 SUPER right now?
The cheapest current listing is $0.18/hr on Clore.ai, and the median across the 2 providers listing it is $0.20/hr. Running one around the clock for a month (730 hours) at the cheapest rate costs about $131.
What AI models can the Nvidia RTX 4070 SUPER run?
With 12 GB it's limited to small models: 7–8B at 4-bit, or 3–4B at higher precision, plus embedding and speech models. It's a budget option for experiments rather than serving.
Which models are recommended for the Nvidia RTX 4070 SUPER?
6 models in our catalog have a recommended configuration for this card, with the quantization that fits its 12 GB — see the AI models tab.
Why does the Nvidia RTX 4070 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 RTX 4070 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.