...

Reserve Cloud 4090 24GB Capacity

OR
Deploy one now from just $0.37/hour!

NVIDIA 4090 24GB:
Best image generation and rendering from $0.37/hr

From computer vision to image generation, the NVIDIA 4090 Tensor Core GPU accelerates the most demanding visual workloads

Up to 60% faster PyTorch performance than the 3090

Up to 80% improvement on FP16 training throughout over the 3090

Clusters continuously coming online through Q1 2024.
Reserve access today, or deploy one now from $0.37/hr.

75 images/min

512x512, stable-diffusion-v1-5, 50 steps, WebUI

24 GB VRAM at 1,008 GB/s

The 4090 has fast, GDDR6X memory for ML workloads

From just $0.37/hr

On TensorDock's cloud platform. See below for more pricing details

... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...

About the NVIDIA 4090

...

About the NVIDIA 4090 GPU

The NVIDIA 4090 is based on NVIDIA's Ada Lovelace GPU architecture. It's a powerhouse in the realm of visual computing GPUs, catering to demanding applications in gaming, data analytics, and computer vision.

The 4090 is fast. Featuring 512 fourth-generation Tensor Cores and 16,384 CUDA Cores, it provides significant improvements in performance for AI and machine learning applications compared to the 3090

Apart from pure performance, its massive 24 GB of VRAM and over 1 TB/s of memory bandwidth make it a strong value for tasks that require large amounts of fast memory.

The 4090 boasts advanced features such as DLSS, which can provide data augmentation for more efficient cloud gaming and rendering sacrificing quality. Overall, the NVIDIA 4090 represents a significant leap forward in GPU technology, offering strong performance and efficiency for the most demanding computing tasks.

See full data sheet.

75 images/min

512x512, stable-diffusion-v1-5, 50 steps, WebUI

16,384 CUDA Cores

CUDA cores are the basic processing units of NVIDIA GPUs. The more CUDA cores, the better.

512 Tensor Cores

Tensor cores are specialized processing units that are designed to efficiently execute matrix operations, used in deep learning.

661 Teraflops FP16

With sparsity.

24 GB VRAM @ over 1 TB/s

The more VRAM, the more data a GPU can store at once. The 4090 24GB has 1,006 GB/s of memory bandwidth.

From just $0.37/hour

Deploy the Powerful NVIDIA 4090 GPU on TensorDock

Unleash unparalleled computing power for on the industry's most cost-effective cloud

NVIDIA 4090

Deploy up to:

  • 8x NVIDIA 4090 GPUs for 192 GB of combined VRAM
  • 2x AMD EPYC 75F3 with 128 combined threads
  • 14 TB local PCIe 4.0 NVMe SSD
  • 10 Gbps of public internet connectivity

Our hostnodes come with beefy resources, ensuring that your work is never bottlenecked by the hardware resources. We have a select number of hostnodes that we offer on-demand. You can deploy 1-8 GPU 4090 virtual machines fully on-demand starting at just $0.37/hour depending on CPU/RAM resources allocated, or $0.20/hour if deployed as a spot instance. We are seeing high demand, so it is difficult to snag a multi-GPU 4090 VM at this time.

As such, we higly recommending contacting us to reserve an entire 8x hostnode from an upcoming batch.

Reserve an 8x 4090 24GB cloud server  Deploy a 4090 24GB cloud server today

Why deploy an NVIDIA 4090 on the TensorDock Cloud?

...

Engineered for Excellence

We built our own hypervisor, our own load balancers, and our own orchestration engine — all so that we can deliver the best performance.

VMs in 10 seconds, not 10 minutes. Instant stock validation. Resource webhooks/callbacks. À la carte resource allocation and resizing.

Save with Storage-Only Pricing

For on-demand servers, when you stop and unreserve your GPUs, you are billed a lower rate for storage. You can always request an export of your VM's disk image.

...
...

Jupyter Notebook made easy

Deploy our machine learning image and get Jupyter Notebook/Lab out of the box. Slash your development setup times.

Reliable, Enterprise-Grade Infrastructure

We have one primary 4090 data center, along with many other hosts across the globe.

    Oregon, United States4090 24GB
    Tier 3 Flexential data center with 24/7 security, 100Gbps redundant network backbone, distributed redundant UPS, and 100% power SLA

Ask about each data center's compliance certifications. Many are SSAE-18 SOC2 Type II, CJIS, HIPAA, & PCI-DSS certified, so you can trust that your most mission-critical workloads are in a safe place.

...
...

More than just 4090s.

Hi! We're TensorDock, and we're building a radically more efficient cloud. Five years ago, we started hosting GPU servers in two basements because we couldn't find a cloud suitable for our own AI projects. Soon, we couldn't keep up with demand, so we built a partner network to source supply.

Today, we operate a global GPU cloud with 27 GPU types located in dozens of cities. Some are owned by us, and some are owned by partners, but all are managed by us.

In addition to GPUs, we also offer CPU-only servers.

We speak in tokens and iterations; in IB and TLC/MLC, and we're excited to serve you.

0

GPUs

0

vCPUs

0

GB RAM

... all deployed within the past 24 hours

Frequenty Asked Questions

?

Where is the 4090 available for deployment?

The 4090 is available for deployment at multiple multihomed tier 1-3 data centers. Each is protected by 24/7 security, powered via redundant feeds, and backed a power and network SLA.

Experience sub-20 ms latencies to key population centers along the US west coast for low-latency LLM inference traffic.

?

How do you guarantee security?

Every layer of our infrastructure is protected by a variety of security measures, ensuring privacy and security for our customers.

Read more about our security.

?

What virtualization? Docker containers?

We're thrilled to offer bare-metal virtualization for customers looking to rent full 8x configurations for a long period of time.

For on-demand customers, we offer KVM virtualization with root access and a dedicated GPU passed through. You get to use the full compute power of your GPU without resource contention.

?

How is billing done?

For our on-demand platform, we operate on a pre-paid model: you deposit money and then provision a server. Once your balance nears $0, the server is automatically deleted. For these 4090s, we are also earmarking a portion to be billed via long term contracts.

Get started

Deploy a 4090 GPU server from $0.37/hour.

Go ahead — go build the future of tomorrow — on TensorDock. Cloud-based machine learning and rendering has never been easier and cheaper.

Deploy a GPU Server
... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ... ...