How much does it cost to rent an NVIDIA A40?

The price for running an NVIDIA A40 on CUDO Compute starts at $0.27/hr with our commitment pricing. See our pricing table to see our full range of available prices or learn more about how commitment pricing works in our documentation.

Do you offer any discounts on NVIDIA A40s for committed use?

Unfortunately we do not currently offer commitment pricing options for the NVIDIA A40 GPU. You can see our full range of GPU pricing options, including commitment prices on our GPU pricing page.

NVIDIA A40

The NVIDIA A40 is a high performing graphics processing unit (GPU) that brings best-in-class professional graphics and powerful computing acceleration together to empower professionals across various domains, including artificial intelligence (AI), high-performance computing (HPC), data analytics, media production, VR and others. Starting from $0.27/hr

Launch an instance Speak with an expert

Available at the most cost-effective pricing

Launch your AI products faster with on-demand GPUs and a global network of data center partners

Virtual machines

The ideal deployment strategy for AI workloads with a A40.

from $0.27/hr

Save up to 35% with commitment pricing Launch an instance

Up to 8 GPUs / virtual machine
Flexible
Network attached storage
Private networks
Security groups
Images

Want to learn more about deploying A40 GPUs with our infrastructure?

Book a demo

Looking to scale? Please contact us for enterprise solutions.

Speak with an expert

The NVIDIA A40 is perfect for a wide range of workloads

Deploying AI based workloads on CUDO Compute is easy and cost-effective. Follow our AI related tutorials.

Deploying LLM’s like Google Gemma

In this tutorial we will run Google Gemma with Ollama so that you can send queries via a Rest API

Read tutorial

Deploy PyTorch

With CUDO Compute you can deploy PyTorch docker containers to the latest NVIDIA Ampere Architecture GPUs.

Read tutorial

Specifications

Starting from	$0.27/hr
Architecture	NVIDIA Ampere
Form factor	PCIe
GPU memory	48GB GDDR6
GPU memory bandwidth	696 GB/s
CUDA cores	10,752
RT cores	84
Tensor cores	336
FP32	37.4 TFLOPS
FP16 tensor core	149.7 \| 299.4 TFLOPS
TF32 tensor core	74.8 \| 149.6 TFLOPS
RT core performance	73.1 TFLOPS
BF16 tensor with FP32 accumulate	149.7 \| 299.4 TFLOPS
INT8 tensor core	299.3 \| 598.6 TOPS
INT4 tensor core	598.7 \| 1,197.4 TOPS
Virtual GPU (vGPU) software support	NVIDIA vPC/vApps, NVIDIA RTX Virtual Workstation, NVIDIA Virtual Compute Server
Decoders	2x NVDEC, 1x NVENC
Compute APIs	CUDA, DirectCompute, OpenCL™, OpenACC®
Graphics APIs	DirectX 12.07, Shader Model 5.17, OpenGL 4.68, Vulkan 1.18
Max thermal design power (TDP)	300W
Multi-instance GPUs (MIG) support	No
Interconnect	NVIDIA® NVLink® 112.5 GB/s (bidirectional) PCIe Gen4: 64GB/s

Use cases

AI & Data Science

Engineers and scientists can deploy the NVIDIA A40 GPU to accelerate their AI/ML workloads. This HPC power delivers cost-effective workload acceleration available on demand and scale to effortlessly process massive datasets to develop, train, and manage AI models.

Virtual Reality (VR) Development

NVIDIA A40 cloud-based GPU helps VR developers create immersive VR experiences. The A40 GPU seamlessly and quickly renders lifelike graphics, allowing organizations to speed up render times and create stunningly realistic graphics at a lower cost.

Video Rendering & Editing

Film production and animation studios can greatly benefit from using the NVIDIA A40 cloud-based GPU. The A40 enables cost-effective and real-time video editing of high-resolution footage, allowing creators to non-destructively edit footage without the typical delays caused by rendering.

Browse alternative GPU solutions for your workloads

Access a wide range of performant NVIDIA and AMD GPUs to accelerate your AI, ML & HPC workloads

NVIDIA H100

Utilise our on-demand cloud and quickly deploy high performing H100 GPUs.

Learn more Deploy

NVIDIA H200

Get the highest performing H200 GPUs at scale on our reserved cloud.

Learn more Get pricing

NVIDIA B100

Get the highest performing B100 GPUs at scale on our reserved cloud.

Learn more Get pricing

NVIDIA L40S

Utilise our on-demand cloud and quickly deploy high performing L40S GPUs.

Learn more Deploy

NVIDIA A100 PCIe

Utilise our on-demand cloud and quickly deploy high performing A100 PCIe GPUs.

Learn more Deploy

NVIDIA V100

Utilise our on-demand cloud and quickly deploy high performing V100 GPUs.

Learn more Deploy

NVIDIA RTX A4000

Utilise our on-demand cloud and quickly deploy high performing RTX A4000 GPUs.

Learn more Deploy

NVIDIA RTX A5000

Utilise our on-demand cloud and quickly deploy high performing RTX A5000 GPUs.

Learn more Deploy

NVIDIA RTX A6000

Utilise our on-demand cloud and quickly deploy high performing RTX A6000 GPUs.

Learn more Deploy

AMD MI250/300

Get the highest performing MI250/300 GPUs at scale on our reserved cloud.

Learn more Get pricing

An NVIDIA preferred partner for compute

We're proud to be an NVIDIA preferred partner for compute, offering the latest GPUs and high-performance computing solutions.

Also trusted by our other key partners:

Frequently asked questions

How much does it cost to rent an NVIDIA A40?: The price for running an NVIDIA A40 on CUDO Compute starts at $0.27/hr with our commitment pricing. See our pricing table to see our full range of available prices or learn more about how commitment pricing works in our documentation.
Do you offer any discounts on NVIDIA A40s for committed use?: Unfortunately we do not currently offer commitment pricing options for the NVIDIA A40 GPU. You can see our full range of GPU pricing options, including commitment prices on our GPU pricing page.

Are you looking for support with something more specific? Check our our knowledge base

Pricing & reservation enquiry

Enquire about access today to test the A40 GPU Cloud, or reserve your A40 Cloud on CUDO Compute for as long as you want it, with unique contracts tailored to suit your needs.

Get started today or speak with an expert...

+44 20 8050 7646

Available Mon-Fri 9am-5pm UK time

Get started Speak with an expert