Skip to content

NVIDIA · Ampere · 2020

NVIDIA RTX 3090. Rental by the hour, on demand.

From $0.41/hr per GPU, pay as you go with no commitment. 24 GB of GDDR6X and 71 TFLOPS FP16 non-tensor, for training and inference.

RTX 3090 on demand

from$0.41/hr per GPU
Availability
Available now · 1 region
By region and size
$0.41 to $0.42/hr
Billing
By the second on most GPUs, a few by the minute
8+ GPUs or a month
Launch any size yourself, or prepay a machine for 1 to 12 months at a discount. Custom quotes on request.

The card

24 GB of GDDR6X. At 936 GB/s.

Memory
24 GB
GDDR6X
Bandwidth
936 GB/s
Memory to compute
FP16
71
non-tensor TFLOPS
Per node
2 GPUs
NVLink, 350 W each

Price across clouds

NVIDIA RTX 3090, cloud by cloud. Sorted by price.

On-demand rates per GPU-hour from each cloud's public price page on 8 Nov 2026: RunPod's Secure Cloud, and Lambda's lowest per-GPU rate across its cluster sizes. Runcrate's row is today's live starting rate.

Runcrate$0.41/hr
RunPod$0.50/hr

Launch it

Ask your agent for an RTX 3090. Or read the call it makes.

Claude Code or Codex runs it for you: it starts the instance, copies your files over and runs the job. The SDKs make the same request.

Connect your agent first

Add Runcrate's MCP server to yourself: run curl -fsSL "https://runcrate.ai/mcp.md" and follow it.

Add to CursorInstall in VS Code
Works inClaude CodeCodexOpenCodeClineRoo CodeKilo CodeCursor

Start an RTX 3090 on Runcrate called my-gpu, copy train.py to it and run it.

MCP callstext
create_instance { name: "my-gpu", gpu: "RTX3090" }
instance_status { id: "my-gpu" }
file_upload { id: "my-gpu", content: "<train.py>", path: "/root/workspace/train.py" }
ssh_execute { id: "my-gpu", command: "nohup python /root/workspace/train.py > train.log 2>&1 &" }

Spec sheet

How the RTX 3090 compares. Against its closest alternatives.

FP16 non-tensor

NVIDIA RTX 309071 TFLOPS
NVIDIA RTX 4070 Ti80.2 TFLOPS
NVIDIA RTX 408097.5 TFLOPS

Memory

NVIDIA RTX 309024 GB
NVIDIA RTX 4070 Ti12 GB
NVIDIA RTX 408016 GB
NVIDIA V10032 GB

Bandwidth

NVIDIA RTX 3090936 GB/s
NVIDIA RTX 4070 Ti504 GB/s
NVIDIA RTX 4080736 GB/s
NVIDIA V100900 GB/s

Alternatives

Alternatives to the RTX 3090. Same account, different price and performance.

GPUMemory · FP16 non-tensorStands outPrice gapFrom
NVIDIA RTX 3090This GPU24 GB GDDR6X · 71 TFLOPS$0.41/hr
NVIDIA RTX 4070 Ti12 GB GDDR6X · 80.2 TFLOPS-12 GB memoryNot in stock right now
NVIDIA RTX 408016 GB GDDR6X · 97.5 TFLOPS-8 GB memoryNot in stock right now
NVIDIA V10032 GB HBM2+8 GB memory+717%$3.35/hr
NVIDIA A4048 GB GDDR6+24 GB memory+549%$2.66/hr

Full specs

NVIDIA RTX 3090 specifications.

Memory

Memory
24 GB
Type
GDDR6X
Bandwidth
936 GB/s

Compute

FP32
35.6 TFLOPS
FP16 non-tensor
71 TFLOPS
INT8
284 TOPS
CUDA cores
10,496

Power and form

TDP
350 W
Form factor
Consumer
Architecture
Ampere
Released
2020

Node

GPUs per node
2
Interconnect
NVLink
Maker
NVIDIA

Questions

Renting the RTX 3090. What buyers ask first.

Other GPUs

Browse every GPU by architecture.