Ampere Architecture
NVIDIA RTX 3090
NVIDIA GeForce RTX 3090 — Rent GPU servers for AI training, inference, and HPC.
Memory
24 GB
GDDR6X
FP32
35.6
TFLOPS
Bandwidth
936
GB/s
Avg. Price
$0.22
per hour
Hardware · Specifications
Full specs.
ManufacturerNVIDIA
ArchitectureAmpere
Release Year2020
VRAM24 GB GDDR6X
Memory Bandwidth936 GB/s
FP32 Performance35.6 TFLOPS
FP16 Performance71 TFLOPS
INT8 Performance284 TOPS
Tensor Cores10496
CUDA/Stream Processors10496
TDP350W
Form FactorConsumer
NVLink SupportYes
Max GPUs per Node2
Compute · Performance
Performance overview.
FP32 Single Precision
35.6
TFLOPS
FP16 Half Precision
71
TFLOPS
INT8 Integer Ops
284
TOPS
Workloads · Use Cases
Ideal for.
AI Prototyping
Content Creation
Budget ML Training
Cost · Pricing
Transparent pricing.
Hourly$0.22/hr
Daily$5.28/day
Monthly$160.60/mo
Platform · Why Runcrate
Why rent NVIDIA RTX 3090.
Deploy in 60 Seconds
Get instant access to NVIDIA RTX 3090. No setup required, start training immediately.
Pay Per Second
Only pay for what you use. Stop instances anytime. No hidden fees.
Enterprise Ready
99.9% uptime guarantee. 24/7 support. Production-grade infrastructure.
Support · FAQ