NVIDIA

GeForce RTX 3090

GeForce RTX 3090 — illustration of the card's form factor
VRAM
24 GB
CUDA Cores
10,496
TDP
350 W
Memory
GDDR6X

Provider Marketplace

Cheapest
$0.09/hour
Starting from
SaladCloud logo
SaladCloudVisit
Best Value
$0.20/hour
Starting from
TensorDock logo
TensorDockVisit
Enterprise Choice
$0.22/hour
Starting from
RunPod logo
RunPodVisit

All Cloud Providers

4 Options available
SaladCloud logo
SaladCloudCheapest
On-Demand
$0.09/ hour
Estimated Cost
Provision
Prime Intellect logo
$0.19/ hour
Estimated Cost
Provision
TensorDock logo
TensorDock
On-Demand
$0.20/ hour
Estimated Cost
Provision
RunPod logo
RunPod
On-Demand
$0.22/ hour
Estimated Cost
Provision

Estimates only — rates are collected automatically from public provider pages and may be out of date. Prices vary by region, commitment term, and availability, and typically exclude storage, egress, and tax. Confirm current pricing with the provider before purchasing. Last collected .

Architecture

MicroarchitectureAmpere
CUDA Cores10496
Tensor Cores3rd Generation
RT Cores2nd Generation
Base Clock1.40 GHz
Boost Clock1.70 GHz

Memory & VRAM

Memory TypeGDDR6X
Total Capacity24 GB
Bus Width384-bit

Connectivity & Scaling

InterconnectNVLink
PCIe InterfaceGen 4

Power & Efficiency

TDP350 W
PSU Required750
Connectors2x PCIe 8-pin (adapter to 1x 12-pin included)
Thermal LimitsMaximum GPU Temperature (in C): 93

Physical Design

Form FactorPCIe
Slot Width3-Slot
Dimensions12.3" (313 mm) x 5.4" (138 mm)

Software Ecosystem

Driver StabilityExtensively tested across thousands of hardware configurations for maximum performance and reliability.

Server & Deployment

PreconfiguredGeForce RTX 3090 Desktops - Greece: GeForce RTX 3090 24GB , Intel Core i9-10900K, 32 GB DDR4 3200 MHz, 500 GB SSD NVMe 4 TB HDD, €3,999*
Ref ArchitecturesNVIDIA Founders Edition / reference graphics card design

System Compatibility

CPU PairingIntel Core i9-10900K (as basis for requirement)
Required PCIePCI Express Gen 4
MotherboardThree unused expansion slots; clearance for a 12.3" (313 mm) x 5.4" (138 mm) x 3-slot card

Benchmarks & Throughput

Scaling Efficiency

A new, smaller connector to link two NVLink SLI-ready 30 Series graphics cards means you can count on super-smooth gameplay and better thermal performance at maximum resolutions with the ultimate visual fidelity.

Multi-GPU Scalability

Scaling Characteristics

ParallelismNVIDIA NVLink (SLI-Ready): Yes; GeForce RTX NVLink Bridge links two NVLink SLI-ready 30 Series graphics cards.

Workload Readiness

Market Authority

Key Strengths

Limitations

Also in the Lineup

NVIDIA
A10
NVIDIA
A100 80GB SXM
NVIDIA
A100 80GB PCIe
NVIDIA
A10G
NVIDIA
A16
NVIDIA
A30
NVIDIA
A40
NVIDIA
B200 SXM

Expert Insight

The GeForce RTX 3090 represents a strategic leap in AI compute. When comparing cloud providers, consider not just the hourly rate, but also the interconnect bandwidth (InfiniBand/NVLink) and regional availability which can significantly impact total cost of ownership for large-scale training.

Glossary Terms

FP32 TFLOPS
VRAM
TDP
Cores
Information updated daily. Cloud pricing subject to vendor availability.