Back to all GPUs

NVIDIA RTX 4090 Cloud GPU Specs

HexGrid Cloud rents the NVIDIA GeForce RTX 4090 at $0.45 per GPU hour, billed per minute — about 39% below the $0.74/hr average across 1 other clouds. The RTX 4090 carries 24GB of GDDR6X memory on the Ada Lovelace architecture.

24GB VRAMAda LovelaceDeploys in ~1 minSecure Cloud

HexGrid Cloud price

$0.45/hr

Billed per minute

VRAM

24GB

GDDR6X

FP32

83 TFLOPS

Compute performance

Market average

$0.74/hr

You save 39%

Running the RTX 4090 on HexGrid Cloud

What you get when you deploy with us, beyond the hourly rate.

Live in under a minute

Pick a region, hit deploy, and SSH in. No quota requests, no sales call.

Per-minute billing

You pay for the minutes you use. Stop the instance and billing stops with it.

Ready for training day one

CUDA, PyTorch and the usual drivers are preinstalled, or bring your own image.

No egress charges

Move checkpoints and datasets out without a surprise bandwidth bill.

RTX 4090 pricing across the market

Published on-demand rates from other clouds, so you can see where our RTX 4090 price sits.

Market average $0.74/hr across 1 cloud

39% below market average
  • HexGrid CloudYou're here$0.45/hr
  • RunPod$0.74/hr

Other providers' rates are their published on-demand list prices. They exclude committed-use discounts and can change at any time. Shown for reference only.

About the NVIDIA GeForce RTX 4090

What the RTX 4090 is built for, and where it falls short.

The NVIDIA GeForce RTX 4090 is a high-performance Ada Lovelace GPU with 24GB of GDDR6X memory. Its strong CUDA performance, fourth-generation Tensor Cores, dual AV1 encoders, and high memory bandwidth make it popular for generative AI, inference, rendering, image generation, video generation, and development workloads.

Best suited for

The RTX 4090 offers very high compute performance and excellent generative AI throughput for its cost, although its 24GB VRAM and lack of enterprise virtualization features limit some workloads.

  • LLM inference
  • Image generation
  • Video generation
  • AI development
  • 3D rendering
  • CUDA workloads

Strengths

  • Very high compute performance
  • Excellent price-to-performance for AI
  • FP8-capable Tensor Cores
  • Dual AV1 encoding
  • Strong rendering performance

Limitations

  • 24GB VRAM
  • No ECC memory
  • No NVLink
  • No MIG or enterprise vGPU support

NVIDIA GeForce RTX 4090 specifications

Full technical specifications for the NVIDIA GeForce RTX 4090.

VendorNVIDIAArchitectureAda LovelaceChipAD102CategoryConsumer GPUReleased2022Form factor3-slotInterfacePCIe 4.0 x16

Memory

Memory
24 GB
Type
GDDR6X
Bandwidth
1,008 GB/s
Bus width
384-bit
ECC
No

Compute

CUDA cores
16,384
Tensor cores
512
Tensor generation
Gen 4
RT cores
128
Boost clock
2,520 MHz

AI & compute performance

FP32
83 TFLOPS
RT
191 TFLOPS

Power & physical

TDP
450 W
Power connector
16-pin PCIe Gen 5
Form factor
3-slot
Cooling
Active
Length
304 mm

Interconnect

Interface
PCIe 4.0 x16
NVLink
No
Infinity Fabric
No

Virtualization

MIG
No
vGPU
No
SR-IOV
No

Media engines

NVENC engines
2
NVDEC engines
1
AV1 encode
Yes
AV1 decode
Yes

Software

CUDA
Yes
ROCm
No

Precision support

FP64
No
FP32
Yes
TF32
Yes
BF16
Yes
FP16
Yes
FP8
Yes
INT8
Yes

RTX 4090 frequently asked questions

Common questions about NVIDIA GeForce RTX 4090 pricing, specifications and workloads on HexGrid Cloud.

How much VRAM does the RTX 4090 have?

The RTX 4090 has 24GB of GDDR6X memory on a 384-bit memory interface.

Is the RTX 4090 good for AI?

Yes. The RTX 4090 provides strong Tensor and CUDA performance and is widely suited to inference, image generation, video generation, and AI development.

Does the RTX 4090 support NVLink?

No. The GeForce RTX 4090 does not support NVLink.

Does the RTX 4090 support AV1 encoding?

Yes. The RTX 4090 includes two eighth-generation NVENC engines with AV1 encoding support.

How much does an RTX 4090 cost per hour?

RTX 4090 cloud pricing varies by provider and region. HexGrid compares current hourly GPU offers.

Other GPUs on HexGrid Cloud

If the RTX 4090 isn't the right fit, these are also available to deploy.

Browse every GPU we rent

Start training on the RTX 4090 today

$0.45 per GPU hour, billed per minute, running in about a minute.

Specification sources