# Cloud runner to use faster, rented GPUs? **URL:** \ **Category:** Ideas\ **Tags:** reviewed\ **Created:** [January 20, 2024, 6:53pm UTC](https://community.topazlabs.com/t/cloud-runner-to-use-faster-rented-gpus/60881 "2024-01-20T18:53:36Z")\ **Posts on this page:** 5\ **Page:** 1
**Author:** ![nada](https://community.topazlabs.com/user_avatar/community.topazlabs.com/nada/32/223673_2.png) [@nada](https://community.topazlabs.com/u/nada)\ **Post date:** [January 20, 2024, 6:53pm UTC](https://community.topazlabs.com/t/cloud-runner-to-use-faster-rented-gpus/60881/1 "2024-01-20T18:53:36Z")
It would be nice if there was a separate server executable you could launch on something like RunPod with a H100 GPU. Then you could run the interface locally as always but send any generation jobs to the server rather than running them locally on much slower hardware. ---
**Author:** ![gene-8240](https://community.topazlabs.com/user_avatar/community.topazlabs.com/gene-8240/32/162024_2.png) [@gene-8240](https://community.topazlabs.com/u/gene-8240)\ **Post date:** [January 20, 2024, 7:00pm UTC](https://community.topazlabs.com/t/cloud-runner-to-use-faster-rented-gpus/60881/2 "2024-01-20T19:00:45Z")
To do this on a Windows PC, create a Virtual Machine, load Windows and TVAI and select the link for the provider’s online GPU as the Virtual Machine’s GPU. That will create a separate instance of TVAI in its own environment that uses the cloud GPU as if it’s local HW. ---
**Author:** ![nada](https://community.topazlabs.com/user_avatar/community.topazlabs.com/nada/32/223673_2.png) [@nada](https://community.topazlabs.com/u/nada)\ **Post date:** [January 20, 2024, 7:51pm UTC](https://community.topazlabs.com/t/cloud-runner-to-use-faster-rented-gpus/60881/3 "2024-01-20T19:51:01Z")
> [@gene-8240](#): > > select the link for the provider’s online GPU as the Virtual Machine’s GPU What do you mean by this? I am not aware of any software that can do that. ---
**Author:** ![gene-8240](https://community.topazlabs.com/user_avatar/community.topazlabs.com/gene-8240/32/162024_2.png) [@gene-8240](https://community.topazlabs.com/u/gene-8240)\ **Post date:** [January 20, 2024, 8:10pm UTC](https://community.topazlabs.com/t/cloud-runner-to-use-faster-rented-gpus/60881/4 "2024-01-20T20:10:25Z")
When you create a VM in Windows, you configure it just like you would a physical one, selecting virtual GPUs, drives, network adapters, etc. In most cases, you just select the physical ones in your own computer, but you can also specify cloud-based substitutes. Windows VM: > **[Step-By-Step: How to Create a Windows 11 VM on Hyper-V via PowerShell](https://techcommunity.microsoft.com/t5/educator-developer-blog/step-by-step-how-to-create-a-windows-11-vm-on-hyper-v-via/ba-p/3754100)** > > This step-by-step guide outlines how to create a Windows 11 virtual machine (VM) on Hyper-V using PowerShell commands. By following these instructions, IT.. Cloud GPUs: > **[GPU Cloud Computing Solutions from NVIDIA](https://www.nvidia.com/en-us/data-center/gpu-cloud-computing/)** > > NVIDIA GPUs are the computing platform that transforms big data into super-human intelligence. Available on-demand on all major cloud platforms. Learn more. ---
**Author:** ![gene-8240](https://community.topazlabs.com/user_avatar/community.topazlabs.com/gene-8240/32/162024_2.png) [@gene-8240](https://community.topazlabs.com/u/gene-8240)\ **Post date:** [January 20, 2024, 8:47pm UTC](https://community.topazlabs.com/t/cloud-runner-to-use-faster-rented-gpus/60881/6 "2024-01-20T20:47:46Z")
I think most modern cloud computing schemes require a provider that is actually running the app on its hardware. The folks at Topaz did mention the possibility of some kind of farm scheme, but IMO the prospects of a commercial SW product using a public access distributed computing system seems doubtful.