Standard RTX 3090 · available
For work that isn't sensitive
Ordinary GPU machines, no enclave. Templates or your own Docker image, SSH, volumes, the API and the CLI. If a launch fails, the prepaid hour comes back.
NVIDIA · 24 GB VRAM
Rent NVIDIA RTX 3090 GPUs, by the second
Single RTX 3090 GPUs on demand from a prepaid balance. No waitlist, no sales call, no contract: launch, work, stop, pay for the seconds you used.
Live stock is on the standard GPUs page.
Confidential RTX 3090 · not available yet
For data you can't expose
No RTX 3090 in Intel TDX confidential mode today. For sensitive data, H100, H200 and RTX PRO 6000 Blackwell run as confidential VMs with attestation you generate yourself.
See confidential VMs →The RTX 3090 in short
- ArchitectureAmpere
- Memory24 GB GDDR6X
- Memory bandwidth936 GB/s
- Performance35.6 TFLOPS FP32
- Power350 W
What people run on an RTX 3090
- Budget local LLM inference with quantized models
- Stable Diffusion image generation and upscaling
- Hobby training runs and CUDA experiments
From zero to a running RTX 3090
- Pick a machine on the standard GPUs page, filtered by GPU, price and stock.
- Launch with a template (PyTorch, vLLM, SGLang…) or your own image, from the console, the API or the CLI.
- Check what you got: one read-only command compares the machine with its listing.
curl -fsSL https://voltagegpu.com/hwcheck.sh | bash -s -- --gpu "RTX 3090" --gpus 1Other GPUs you can rent
B300 · B200 · H200 · H100 · RTX 5090 · RTX 4090 · A100 · A6000 · L40S · RTX A4000 · RTX A5000