NVIDIA RTX 3090

Cloud GPU Pricing — Live from 8+ Providers
Starting From
$0.100/hr
5 on-demand listings
VRAM
24 GB GDDR6X
Architecture
Ampere
FP16 Performance
71 TFLOPS
Memory Bandwidth
936 GB/s
Listings
8 options
Provider Pricing
ProviderPrice / hrEst. MonthlyTypeVRAMAction
BestSalad Cloud $0.1000/hr $73/mo On-Demand 24 GB Rent Now →
TensorDock $0.2000/hr $146/mo On-Demand 24 GB Rent Now →
Vast.ai $0.2022/hr $147.61/mo On-Demand 24 GB Rent Now →
RunPod $0.4600/hr $335.8/mo On-Demand 24 GB Rent Now →
RunPod $0.4600/hr $335.8/mo On-Demand 24 GB Rent Now →
Vast.ai $0.1342/hr $97.97/mo Spot 24 GB Rent Now →
RunPod $0.2200/hr $160.6/mo Spot 24 GB Rent Now →
RunPod $0.2700/hr $197.1/mo Spot 24 GB Rent Now →
About the NVIDIA RTX 3090

The NVIDIA RTX 3090 is the budget-friendly option for 24 GB VRAM workloads. With the same VRAM as the RTX 4090 at a lower cost, it is popular for running quantized LLMs, Stable Diffusion pipelines, and small model fine-tuning. Great value when inference throughput is not the priority.

GPU Specifications
VRAM24 GB GDDR6X
ArchitectureAmpere
FP16 Performance71 TFLOPS
Memory Bandwidth936 GB/s
TDP350W
InterconnectPCIe 4.0
Best For
LLM InferenceStable DiffusionSmall Model TrainingQuantized Inference

Compare All NVIDIA RTX 3090 Options Side by Side

Filter by price type, sort by cost, and find the best deal for your workload.

Open Full Comparison →