Skip to content
GPUVerse Blog

NVIDIA · Ada Lovelace · RTX 40

RTX 4090

24 GB of GDDR6X at 1.0 TB/s, built for inference, fine-tuning.

From $0.59/hrindicative · across 2 providers

RTX 4090 render

Specifications

Memory

24 GB

GDDR6X

Bandwidth

1.01 TB/s

FP16 tensor

330 TFLOPS

FP8 tensor

660 TFLOPS

Interconnect

PCIe

TDP

450 W

CUDA cores

16,384

Tensor cores

512

Where to rent it

ProviderTypeSpotDetails
RunPod logoRunPodneocloudYesView
Vast.ai logoVast.aimarketplaceYesView

Compare with

A100 40GB render
NVIDIA · Ampere

A100 40GB

Memory
40 GB HBM2e
Bandwidth
1.6 TB/s
midfrom$1.29/hr
A100 80GB render
NVIDIA · Ampere

A100 80GB

Memory
80 GB HBM2e
Bandwidth
2.0 TB/s
midfrom$1.19/hr
L40S render
NVIDIA · Ada Lovelace

L40S

Memory
48 GB GDDR6
Bandwidth
0.9 TB/s
midfrom$1.19/hr
A10 render
NVIDIA · Ampere

A10

Memory
24 GB GDDR6
Bandwidth
0.6 TB/s
budgetfrom$0.75/hr