QuantaCloud GPUs on DeployGPU

The QuantaCloud offers on DeployGPU are GPU virtual machines from QuantaCloud, a GPU cloud run by Quanta Cloud LLC, the same company that runs DeployGPU. They launch and bill like every other provider here: from your DeployGPU balance, with no separate QuantaCloud account, and with SSH as ubuntu on port 22. The one hard rule is the key type: QuantaCloud accepts RSA and Ed25519 keys, not ECDSA.

Offers now

46

From

$0.48/GPU-hr

GPUs per VM

1x, 2x, 4x, 8x

GPU models

8

United States · checked 2026-10-13 12:45 UTC

QuantaCloud GPUs you can launch now

Each row is one GPU family in stock on QuantaCloud right now, with the number of VM offers, the GPU counts per VM, the countries and the cheapest price per GPU-hour, refreshed every 15 minutes. The prices are what you pay on DeployGPU, including any platform fee.

For QuantaCloud's prices next to the rest of the market, see QuantaCloud on GpuPerHour.

Same company, listed like any other provider

Quanta Cloud LLC runs DeployGPU, GpuPerHour and QuantaCloud, as the about page explains. On DeployGPU, QuantaCloud offers sit in the same marketplace, the same API and the same live tables as the other providers, sorted by price. One place treats them differently: the Templates page in the dashboard suggests a few GPUs to start with, lists QuantaCloud offers first under the label "Our cloud", and keeps them there even when another provider has the same GPU for less. The full marketplace, one click away from that page, shows every offer by price.

How a QuantaCloud VM differs from the other 3 VM providers

Use an RSA or Ed25519 key

QuantaCloud installs only RSA and Ed25519 keys. If the only key on a launch is ECDSA, there is nothing to install, and the launch fails with SSH_KEY_MISSING before the machine is yours. The Default Key DeployGPU creates at signup is Ed25519, so it works, and so does any key you make with:

ssh-keygen -t ed25519 -C "deploygpu"

Add the public half on the SSH keys page, then select it on the deploy page, which pre-selects the key you used most recently. The SSH guide covers the rest, and the provisioning failures guide lists the other launch errors.

Running means the setup has finished

QuantaCloud reports a VM as running only after its startup script has run, so by the time the dashboard shows Running, the machine has booted and done its setup. Hyperstack, by contrast, reports ready as soon as the VM has a public IP, which is why its first SSH attempt can be refused for a short while.

Disk, templates and what you pay

The disk is fixed per offer and QuantaCloud has no volumes on DeployGPU, so copy anything you want to keep off the VM before you stop it: stopping deletes the VM and its disk. The stop guide has the checklist. All four templates run on QuantaCloud, and template apps open on a private HTTPS link that only your DeployGPU login can use.

The hourly price is the rate you are billed, and launching reserves the first hour. When you stop, the unused seconds of the current hour go back to your balance, and a launch that fails is refunded in full. Card top-ups carry a 5% + $0.30 processing fee. The cost calculator works out a run from live prices.