NVIDIA

NVIDIA · Ampere · 2020

NVIDIA RTX 3090.

Rent the NVIDIA RTX 3090 for AI training and inference. 24GB GDDR6X, 71 TFLOPS FP16, deploy in 60 seconds.

24 GB
GDDR6X
936 GB/s
Bandwidth
71
TFLOPS FP16
2× GPU
NVLink
Available now · 4 regions

Cloud rental

$0.22/hr

On-demand · per-second billing

$0.12$0.28/hr range

Or $0.15/hr reserved (30% off)

Deploy

One command. NVIDIA RTX 3090 in 60 seconds.

Skip the dashboard if you don't need it. SDK, Python, or cURL — copy the snippet, paste your API key, ship.

import Runcrate from "@runcrate/sdk";

const rc = new Runcrate({ apiKey: "rc_live_••••••••••••••••" });

const instance = await rc.instances.create({
  gpu: "rtx-3090",
  region: "auto",
  image: "runcrate/vllm:latest",
});

console.log(`SSH: ssh root@${instance.host}`);

Benchmarks

How NVIDIA RTX 3090 stacks up.

Side-by-side specs vs the closest alternatives. Bars are normalized to the highest value in each metric.

FP16

NVIDIA RTX 309071 TFLOPS
NVIDIA RTX 4070 Ti80.2 TFLOPS
NVIDIA RTX 408097.4 TFLOPS
NVIDIA RTX 4090165 TFLOPS

VRAM

NVIDIA RTX 309024 GB
NVIDIA RTX 4070 Ti12 GB
NVIDIA RTX 408016 GB
NVIDIA RTX 409024 GB

Bandwidth

NVIDIA RTX 3090936 GB/s
NVIDIA RTX 4070 Ti504 GB/s
NVIDIA RTX 4080736 GB/s
NVIDIA RTX 40901.0 TB/s

Full specs

NVIDIA RTX 3090 specifications.

Memory

VRAM24 GB
Memory typeGDDR6X
Bandwidth936 GB/s

Compute

FP3235.6 TFLOPS
FP1671 TFLOPS
INT8284 TOPS
Tensor cores10,496
CUDA cores10,496

Power & form factor

TDP350 W
Form factorConsumer
ArchitectureAmpere
Released2020

Cluster

Max GPUs/node2
InterconnectNVLink
ManufacturerNVIDIA
Available regions4

FAQ

Frequently asked.

Ready when you are

Deploy NVIDIA RTX 3090
in 60 seconds.

Available across 4 regions · per-second billing · no commitments. Ship today.