Why choose the RTX 4070?

12GB GDDR6X with Ada Lovelace architecture. Entry-level Ada GPU for basic AI experimentation.

When is the RTX 4070 not a good fit?

12GB VRAM is insufficient for most LLMs at FP16. Subject to Nvidia's consumer EULA, which may restrict data center use.

Are RTX 4070 prices going up or down?

The median on-demand price across providers has fallen about 25% since August 2025, from $0.12 to $0.09/hr per GPU. This reflects the market-wide median, which moves both when providers change prices and when lower or higher priced offerings enter the market.

What size AI models can the RTX 4070 run?

With 12GB of VRAM, the RTX 4070 is best for 7B-class models in 4-bit or 8-bit quantized form, and smaller models in FP16.

How much VRAM does the RTX 4070 have?

The RTX 4070 has 12GB of VRAM. Multi-GPU setups increase total memory, but that memory is not automatically pooled across GPUs.

What is the RTX 4070's memory bandwidth?

The RTX 4070 has 504 GB/s of memory bandwidth. Higher bandwidth helps with faster data transfer between GPU memory and compute cores.

What data types does the RTX 4070 support?

The RTX 4070 supports 7 precision formats. Training: BF16, FP16, TF32, FP32. Inference: FP8, INT4, INT8.

Does the RTX 4070 support NVLink?

No. The RTX 4070 is a PCIe-only GPU with no NVLink, so it is better suited to single-GPU inference and smaller-scale workloads than large distributed training jobs.

How much does the RTX 4070 cost per hour?

RTX 4070 pricing currently ranges from $0.02/hr to $0.17/hr per GPU, depending on the provider, instance type, and billing model.

How much does the RTX 4070 cost per month?

At 720 hours per month, one RTX 4070 can cost between $11.23 to $122.40 per month, depending on the provider. Reserved and spot pricing can lower that further.

Which cloud providers offer the RTX 4070?

The RTX 4070 is available from 3 cloud providers: Salad, Theta EdgeCloud, Vast.ai.

Can I rent the RTX 4070 in the cloud?

Yes. We currently track 13 RTX 4070 listings across 3 cloud providers: Billing type Listings Avg $/GPU/hr On-demand 6 $0.09/hr Reserved 3 $0.08/hr Spot 4 $0.05/hr

Nvidia RTX 4070

Entry-level Ada Lovelace GPU for prototyping and content creation.

Last update 9 minutes ago

Compare vs other GPUs →

Aggregating historical prices...

Key Specifications

Architecture

Ada Lovelace

Memory

12GB GDDR6X

Memory Bandwidth

504 GB/s

Release date

Q2 2023

RTX 4070 Pricing and Availability

You can start using a RTX 4070 for $0.07/hr per GPU (on-demand). It's a low-risk price point for smaller workloads compared to the market high of $0.17/hr. Spot instances start lower, at $0.02/hr per GPU.

3 providers

How this list works

The two views

By provider shows one card per company, placed where its best offer ranked. By configuration lists every offer.

Order

What you can rent comes first: in stock, then waitlist, then not reported, then out of stock. Priced offers rank ahead of quote-only, and on-demand ahead of other billing types.

Within a group, five factors set the order, largest first:

Location: datacenter proximity, blended with provider HQ.
Price: hourly price, per GPU and in total.
Billing type: reserved ahead of spot, spot ahead of quote-only.
Specs: more VRAM, vCPUs and RAM.
Provider diversity: in By configuration, a provider's repeat rows rank slightly lower, so one company can't take all the top spots.

Search

We match the provider, GPU model, form factor, billing type, availability and instance name. Matching is partial and case-insensitive. Everyday words work too, so "interruptible" finds spot and "sold out" finds out of stock.

Transparency and funding

Ads and sponsors: Paid placements sit at the top of the list and are always labeled as sponsored content. Sponsorship never influences the organic ranking itself.
Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.
Prices: Shown in USD, converted at daily reference rates where a provider publishes in another currency. A month means 720 hours. How we estimate costs.

Vast.ai Our sponsor

USA 11 configs 1x-8x

On-Demand from $0.07 Reserved from $0.06 Spot from $0.0156

From $0.07 / GPU / hr On-Demand Visit website

Theta EdgeCloud In stock

USA 1 config 1x

On-Demand from $0.17

From $0.17 / GPU / hr On-Demand Visit website


1x RTX 4070	11GB	28	31GB	On-Demand	$0.17	$0.17	In stock

Salad

USA 1 config 1x

On-Demand from $0.09

From $0.09 / GPU / hr On-Demand Visit website


1x RTX 4070	12GB	4	8GB	On-Demand	$0.09	$0.09	Not reported

Heads up: We do our best to keep these specs & prices accurate. However, cloud costs may fluctuate based on region, usage, and other factors not listed here. These are estimates based on common setups and are for informational purposes only. Always verify current rates & exact specs with the provider before provisioning.

Frequently Asked Questions

Why choose the RTX 4070?: 12GB GDDR6X with Ada Lovelace architecture. Entry-level Ada GPU for basic AI experimentation.
When is the RTX 4070 not a good fit?: 12GB VRAM is insufficient for most LLMs at FP16. Subject to Nvidia's consumer EULA, which may restrict data center use.
Are RTX 4070 prices going up or down?: The median on-demand price across providers has fallen about 25% since August 2025, from $0.12 to $0.09/hr per GPU. This reflects the market-wide median, which moves both when providers change prices and when lower or higher priced offerings enter the market.
What size AI models can the RTX 4070 run?: With 12GB of VRAM, the RTX 4070 is best for 7B-class models in 4-bit or 8-bit quantized form, and smaller models in FP16.
How much VRAM does the RTX 4070 have?: The RTX 4070 has 12GB of VRAM. Multi-GPU setups increase total memory, but that memory is not automatically pooled across GPUs.
What is the RTX 4070's memory bandwidth?: The RTX 4070 has 504 GB/s of memory bandwidth. Higher bandwidth helps with faster data transfer between GPU memory and compute cores.
What data types does the RTX 4070 support?: The RTX 4070 supports 7 precision formats. Training: BF16, FP16, TF32, FP32. Inference: FP8, INT4, INT8.
Does the RTX 4070 support NVLink?: No. The RTX 4070 is a PCIe-only GPU with no NVLink, so it is better suited to single-GPU inference and smaller-scale workloads than large distributed training jobs.
How much does the RTX 4070 cost per hour?: RTX 4070 pricing currently ranges from $0.02/hr to $0.17/hr per GPU, depending on the provider, instance type, and billing model.
How much does the RTX 4070 cost per month?: At 720 hours per month, one RTX 4070 can cost between $11.23 to $122.40 per month, depending on the provider. Reserved and spot pricing can lower that further.
Which cloud providers offer the RTX 4070?: The RTX 4070 is available from 3 cloud providers: Salad, Theta EdgeCloud, Vast.ai.
Can I rent the RTX 4070 in the cloud?: Yes. We currently track 13 RTX 4070 listings across 3 cloud providers:

Billing type Listings Avg $/GPU/hr

On-demand 6 $0.09/hr

Reserved 3 $0.08/hr

Spot 4 $0.05/hr