Why choose the RTX 3090?

24GB GDDR6X with NVLink support (112 GB/s). One of few consumer GPUs supporting NVLink for 2-GPU configurations. Popular legacy choice for AI researchers.

When is the RTX 3090 not a good fit?

Ampere consumer GPU - no FP8. High power consumption. Subject to Nvidia's consumer EULA, which may restrict data center use. For new setups, the RTX 4090 or RTX 5090 are significantly faster.

Are RTX 3090 prices going up or down?

The median on-demand price across providers has fallen about 25% since August 2025, from $0.17 to $0.13/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 3090 run?

With 24GB of VRAM, the RTX 3090 can typically run 7B to 13B models in FP16, or larger models in 4-bit quantized form.

How much VRAM does the RTX 3090 have?

The RTX 3090 has 24GB of VRAM. Multi-GPU setups increase total memory, but that memory is not automatically pooled across GPUs.

What is the RTX 3090's memory bandwidth?

The RTX 3090 has 936 GB/s of memory bandwidth. Higher bandwidth helps with faster data transfer between GPU memory and compute cores.

What data types does the RTX 3090 support?

The RTX 3090 supports 6 precision formats. Training: BF16, FP16, TF32, FP32. Inference: INT4, INT8.

Does the RTX 3090 support NVLink?

Yes. The RTX 3090 supports NVLink with 112 GB/s of bidirectional bandwidth. This helps accelerate multi-GPU communication.

How much does the RTX 3090 cost per hour?

RTX 3090 pricing currently ranges from $0.05/hr to $0.50/hr per GPU, depending on the provider, instance type, and billing model.

How much does the RTX 3090 cost per month?

At 720 hours per month, one RTX 3090 can cost between $38.66 to $360.00 per month, depending on the provider. Reserved and spot pricing can lower that further.

Which cloud providers offer the RTX 3090?

The RTX 3090 is available from 8 cloud providers, including Runpod, Salad, SwissGPU. Pricing and availability vary by region and billing model.

Can I rent the RTX 3090 in the cloud?

Yes. We currently track 36 RTX 3090 listings across 8 cloud providers: Billing type Listings Avg $/GPU/hr On-demand 21 $0.18/hr Reserved 9 $0.09/hr Spot 6 $0.09/hr

Nvidia RTX 3090

Popular legacy consumer GPU for local AI development with NVLink.

Last update 10 minutes ago

Compare vs other GPUs →

Aggregating historical prices...

Key Specifications

Architecture

Ampere

Memory

24GB GDDR6X

Memory Bandwidth

936 GB/s

Release date

Q3 2020

RTX 3090 Pricing and Availability

You can start using a RTX 3090 for $0.09/hr per GPU (on-demand). It's a low-risk price point for smaller workloads compared to the market high of $0.50/hr. Spot instances start lower, at $0.05/hr per GPU.

8 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 15 configs 1x-8x

On-Demand from $0.10 Reserved from $0.12 Spot from $0.05

From $0.10 / GPU / hr On-Demand Visit website

Theta EdgeCloud In stock

USA 1 config 1x

On-Demand from $0.12

From $0.12 / GPU / hr On-Demand Visit website


1x RTX 3090	24GB	28	15GB	On-Demand	$0.12	$0.12	In stock

Runpod In stock

USA 5 configs 1x-8x

On-Demand from $0.22 Reserved on request

From $0.22 / GPU / hr On-Demand Visit website


1x RTX 3090 Community Cloud	24GB	8	24GB	On-Demand	$0.22	$0.22	In stock
2x RTX 3090 Community Cloud	48GB	16	48GB	On-Demand	$0.22	$0.44	In stock
1x RTX 3090 Secure Cloud	24GB	8	24GB	On-Demand	$0.50	$0.50	In stock
2x RTX 3090 Secure Cloud	48GB	16	48GB	On-Demand	$0.50	$1.00	In stock
8x RTX 3090 Secure Cloud	192GB	64	192GB	Reservation	Custom	Custom	Not reported

GPU.ai In stock

UAE 4 configs 1x-8x

On-Demand from $0.13

From $0.13 / GPU / hr On-Demand Visit website


1x RTX 3090	24GB	--	--	On-Demand	$0.14	$0.14	In stock
2x RTX 3090	48GB	--	--	On-Demand	$0.13	$0.26	In stock
4x RTX 3090	96GB	--	--	On-Demand	$0.15	$0.60	In stock
8x RTX 3090	192GB	--	--	On-Demand	$0.13	$1.02	In stock

HyperAI In stock

Hong Kong 8 configs 1x-8x

On-Demand from $0.10 Reserved from $0.06

From $0.10 / GPU / hr On-Demand Visit website


1x RTX 3090 rtx-3090	24GB	8	24GB	Reserved (1mo)	$0.06	$0.06	In stock
1x RTX 3090 rtx-3090	24GB	8	24GB	On-Demand	$0.10	$0.10	In stock
2x RTX 3090 rtx-3090-2	48GB	16	48GB	Reserved (1mo)	$0.06	$0.12	In stock
2x RTX 3090 rtx-3090-2	48GB	16	48GB	On-Demand	$0.10	$0.20	In stock
4x RTX 3090 rtx-3090-4	96GB	32	96GB	Reserved (1mo)	$0.06	$0.24	In stock
4x RTX 3090 rtx-3090-4	96GB	32	96GB	On-Demand	$0.10	$0.40	In stock
8x RTX 3090 rtx-3090-8	192GB	64	192GB	Reserved (1mo)	$0.06	$0.48	In stock
8x RTX 3090 rtx-3090-8	192GB	64	192GB	On-Demand	$0.10	$0.80	In stock

Salad

USA 1 config 1x

On-Demand from $0.09

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


1x RTX 3090	24GB	4	8GB	On-Demand	$0.09	$0.09	Not reported

TensorDock

USA 1 config 1x

On-Demand from $0.31

From $0.31 / GPU / hr On-Demand Visit website


1x RTX 3090	24GB	16	32GB	On-Demand	$0.31	$0.31	Not reported

SwissGPU

Switzerland 1 config 1x

On-Demand from $0.31

From $0.31 / GPU / hr On-Demand Visit website


1x RTX 3090 RTX 3090	24GB	12	32GB	On-Demand	$0.31	$0.31	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 3090?: 24GB GDDR6X with NVLink support (112 GB/s). One of few consumer GPUs supporting NVLink for 2-GPU configurations. Popular legacy choice for AI researchers.
When is the RTX 3090 not a good fit?: Ampere consumer GPU - no FP8. High power consumption. Subject to Nvidia's consumer EULA, which may restrict data center use. For new setups, the RTX 4090 or RTX 5090 are significantly faster.
Are RTX 3090 prices going up or down?: The median on-demand price across providers has fallen about 25% since August 2025, from $0.17 to $0.13/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 3090 run?: With 24GB of VRAM, the RTX 3090 can typically run 7B to 13B models in FP16, or larger models in 4-bit quantized form.
How much VRAM does the RTX 3090 have?: The RTX 3090 has 24GB of VRAM. Multi-GPU setups increase total memory, but that memory is not automatically pooled across GPUs.
What is the RTX 3090's memory bandwidth?: The RTX 3090 has 936 GB/s of memory bandwidth. Higher bandwidth helps with faster data transfer between GPU memory and compute cores.
What data types does the RTX 3090 support?: The RTX 3090 supports 6 precision formats. Training: BF16, FP16, TF32, FP32. Inference: INT4, INT8.
Does the RTX 3090 support NVLink?: Yes. The RTX 3090 supports NVLink with 112 GB/s of bidirectional bandwidth. This helps accelerate multi-GPU communication.
How much does the RTX 3090 cost per hour?: RTX 3090 pricing currently ranges from $0.05/hr to $0.50/hr per GPU, depending on the provider, instance type, and billing model.
How much does the RTX 3090 cost per month?: At 720 hours per month, one RTX 3090 can cost between $38.66 to $360.00 per month, depending on the provider. Reserved and spot pricing can lower that further.
Which cloud providers offer the RTX 3090?: The RTX 3090 is available from 8 cloud providers, including Runpod, Salad, SwissGPU. Pricing and availability vary by region and billing model.
Can I rent the RTX 3090 in the cloud?: Yes. We currently track 36 RTX 3090 listings across 8 cloud providers:

Billing type Listings Avg $/GPU/hr

On-demand 21 $0.18/hr

Reserved 9 $0.09/hr

Spot 6 $0.09/hr