Cloud VPS 6 GB
Fits small models only, so check the RAM table first. Also suits a chat app that uses a model elsewhere.
$24.99per month
- 6 GB RAM
- 4 vCPU cores
- 100 GB NVMe SSD
- 30 TB
- Unlimited
RUN YOUR OWN AI MODEL
Self Hosted LLM on a Server You Control
A self-hosted LLM is an open AI model that runs on a server you control, so prompts sent to it stay there. xCloud installs Ollama and chat apps in one click, for developers and privacy-minded teams. The Cloud VPS plans below start at $24.99 a month, or connect your own server.
- Download AI models from your dashboard, with no terminal
- HTTPS on your domain
- Use our Cloud VPS or your own GPU server
ONE-CLICK APPS
Which Apps Run a Self-Hosted LLM on xCloud?
Ollama or LocalAI runs the model. The chat apps give people a screen to use it. Each app has its own page with setup details.
Ollama
Runs the model
Downloads open AI models and runs them, so your chat apps and software can use them. Start here. The chat apps need a model to talk to.
Ollama hosting
OpenWebUI
Private team chat
A chat screen for your team. It works with Ollama and with AI services built to work like OpenAI's.
OpenWebUI hosting
LibreChat
Local and hosted models
One AI workspace for Ollama and hosted providers, with agents your team can set up.
LibreChat hosting
AnythingLLM
Chat with your documents
A private workspace for your files. It ships no model, so you connect an Ollama host or another provider. We have not tested AnythingLLM with an Ollama site on xCloud. Ollama is closed to other apps by default, and it has no login.
AnythingLLM hosting
Hollama
Minimal chat screen
A light web chat for Ollama that keeps chats in the browser. We have not tested Hollama with an Ollama site on xCloud. It may need extra setup, and it may mean opening Ollama to the internet.
Hollama hosting
LocalAI
Works with OpenAI-style software
Another way to run models, with its own web screen and sign-in. It also works with software built for OpenAI. This install runs on CPU only.
LocalAI hosting
HOW IT WORKS
How Do You Run Your Own LLM on xCloud?
Four steps from an empty account to a private chat. You do not need to open a terminal.
Create a server
Click New Server and pick Ollama under App Type. Choose a size and region, and keep NGINX selected.
Install Ollama
Click New Site, pick your server, open One Click Apps and choose Ollama. xCloud checks for 15 GB of free disk space first.
Pull a model
Open Ollama → Management, click Add New Model, choose one from the list and click Pull Model.
Add a chat screen
Install OpenWebUI or LibreChat on the same server. Turn on Enable Ollama and pick up to 3 models.
HARDWARE
How Much RAM Does a Self-Hosted LLM Need?
The model decides. xCloud's rule is at least 20 to 30 percent more RAM than the model's size. This table applies 30 percent to sizes listed in xCloud's model picker.
| Model | Size in xCloud's list | Minimum RAM (size + 30%) |
|---|---|---|
| tinyllama:latest | 638 MB | 0.9 GB |
| llama3.2:latest | 2.0 GB | 2.6 GB |
| mistral:latest | 4.4 GB | 5.8 GB |
| deepseek-r1:14b | 9.0 GB | 11.7 GB |
| qwen3:32b | 20 GB | 26 GB |
| llama3.1:70b | 43 GB | 55.9 GB |
| deepseek-r1:671b | 404 GB | 525.2 GB |
These are minimums. Your server may need more. It also needs RAM for the operating system and any other app on it, and the model files take up disk space too. xCloud has not measured how fast these models run on each server size. Models marked Cloud run on Ollama's servers, so those prompts leave your server.
APP MINIMUMS
What Does Each App Need Before the Model?
These are xCloud's install minimums. Add them to your model's minimum RAM when you run several apps on one server.
| App | RAM | CPU | Disk |
|---|---|---|---|
| Ollama | Depends on the model | No minimum set | 15 GB free |
| OpenWebUI | No minimum set | No minimum set | 5 GB free |
| LibreChat | No minimum set | No minimum set | 5 GB free |
| AnythingLLM | 2 GB | 2 cores | 10 GB |
| Hollama | 256 MB | 1 core | 1 GB |
| LocalAI | 4 GB, plus your models | 2 cores | 20 GB, plus your models |
"No minimum set" means xCloud does not check this before install. It does not mean the app needs nothing. If you turn on Enable Ollama during install, OpenWebUI and LibreChat need 15 GB free.
WHY SELF-HOST
Why Self-Host an LLM Instead of Using an API?
You get control over where your prompts go. xCloud handles the setup work around the model.
Prompts stay on your server
With a local model, chats and prompts stay on your server instead of going to a hosted API.
No charge for each request
Ollama does not charge for each request on your own server. You pay for the server.
Your choice of server
Use an xCloud Cloud VPS, or connect a server or GPU machine from your own provider.
Models from your dashboard
Add and remove models in Ollama → Management, without a terminal session.
HTTPS on your domain
xCloud publishes the app on your domain with a free SSL certificate.
24/7 live chat
On paid servers, ask our support team when a server or install needs a closer look.
THE HONEST VIEW
When Is a Hosted API the Better Choice?
Self-hosting is not always the right call. If you need the newest hosted models or have no time for upkeep, an API may suit you better.
| Self-hosted LLM | Hosted API | |
|---|---|---|
| Where prompts go | Your server, unless you connect a hosted provider in a chat app. Models marked Cloud run on Ollama's servers, so those prompts leave your server. | The provider's servers |
| What you pay | A server bill, with no charge for each request from Ollama | The provider's usage fees |
| Which models | Open models from Ollama's library | The provider's own models |
| What sets the speed | Your hardware. CPU is slower than GPU, and bigger models are slower | The provider |
| Who updates it | You. Nothing upgrades on its own | The provider |
| Who controls access | You. Ollama has no login of its own | The provider, through API keys |
Open models may not match hosted ones. Try one on your own work before you commit.
What Does It Cost on an xCloud Server?
Dedicated Cloud VPS sizes with Ollama ready to install. Pick the size that fits your model's minimum RAM.
Cloud VPS 16 GB
Most popularMore room for a model, the operating system and a chat app. Check the RAM table first.
$59.99per month
- 16 GB RAM
- 6 vCPU cores
- 200 GB NVMe SSD
- 30 TB
- Unlimited
Cloud VPS 24 GB
For a larger model, or Ollama beside other apps on one server.
$84.99per month
- 24 GB RAM
- 8 vCPU cores
- 300 GB NVMe SSD
- 30 TB
- Unlimited
Billed monthly with no lock-in. As of November 2026, Ollama itself is free under the MIT License. These servers run on CPU, and the largest published models need far more than 24 GB, so connect your own server for those.
Already Have a Server? Bring Your Own
Connect a VPS or GPU machine from your provider and install the same apps through the same dashboard. If it has an NVIDIA or AMD GPU, xCloud detects it and picks the matching Ollama setup.
Free
Start your journey without cost.
$0forever
- 1 server
- 10 sites
Starter
Most popularYour rate with 2–5 servers connected.
$5per server / month
- 2–5 servers
- Unlimited sites
- All features included
- Bring any VPS provider
Professional
The same platform, discounted at 6–10 servers.
$4per server / month
- 6–10 servers
- Unlimited sites
- All features included
- Bring any VPS provider
Agency
The same platform, discounted at 11+ servers.
$3per server / month
- 11+ servers
- Unlimited sites
- All features included
- Bring any VPS provider
You pay your own provider for the server. This is the path to a GPU machine, because our Cloud VPS sizes run on CPU. The Free plan cannot install Ollama, OpenWebUI or LibreChat, so use a paid server for them.
Hear what people are saying about us
See why agencies, developers, startups, and growing businesses choose xCloud to power their projects.
xCloud works really well, I am surprised by its performance being this the release version, I have tried many paid platforms such as runcloud, cloudpages or serveravatar, as well as free platforms such as CyberPanel, CloudPanel or Hestia Control Panel and direct competitors such as SpinupWP and FlyWP. Of all those that I have tried, the platform that works best for WordPress is SpinupWP and I believe that xCloud can reach and surpass that development, its roadmap is promising. Congratulations to the xCloud team, I hope they become the leading platform in the segment, it has all the potential to achieve it!
Brian GeovannyI've been with runcloud for the last 3 years. However, after trying xcloud for the last month, I'm switching over. They are on a roll with their setup.
Kevin PinedaI'm moving my servers to xCloud, a cloud control panel by M Asif Rahman and the WPDeveloper team. Their roadmap looks interesting and no, there are no team mates nor API limits with xCloud! #xCloud #wordpress #hosting
Leo KooHow Cloud Nine Web Elevated Client Experience While Streamlining Hosting Operations using xCloud
Ed EllinghamxCloud is like having an expert server team on call — without the big agency costs. It's given me back my time and given my clients peace of mind. Highly recommended for freelancers and small teams who want reliable performance and security.
Dumitru ButucelxCloud isn't just a solution. It's like one of that friend who got your back when you screw things up pretty bad.
Waqar AhmedTrust me when I say, once people explore the potential of xCloud they gonna switch from other panels, just keep delivering the best tech, lots of love for the team 😍😍
Rahul SinghSo far my experience has been smooth like silk. I didn't imagine that configuring and managing a VPS would be so easy. As of today, I have deployed 8 sites. The support is good, and they treat users with respect, even if they ask stupid questions (myself included). For the future, I hope for greater flexibility in scheduled backups and more comprehensive and consistent documentation. I'm sure that within a few months, xCloud will become the leader in its segment. This community is amazing, and the Staff here is super helpful.
Massimo VillaCame from cloudways then to runcloud then to xcloud. Looks like I'm staying here.
Gerson ElI've recently taken all of my Vultr-hosted sites and gotten rid of cPanel for them to substitute it with xCloud. I have to say, I'm really impressed with xCloud so far! The interface is definitely the standout feature for me.
Tony LewisI came from Cloudways and won't go back. Highly impressed with xCloud. Glad I gave them a chance.
Jared McDowellI like xCloud better than RunCloud, but one thing I'll point out is that some years ago RunCloud was hungry for business, the support was outstanding, and the community was active and helped each other. Maybe it was sold, there was a change in management, or they stopped being hungry, but the quality of the RunCloud offering declined and it hasn't been moving forward quickly. My point is that currently the xCloud team has the edge and it is theirs to keep or lose
David McCanHow Kevin Heinrichs Cut Hosting Costs by 84% While Running WooCommerce & Node.js Sites Efficiently
Kevin HeinrichsI had 150 sites on cloudways and am in the process of moving them to xcloud. Much faster and better priced.
Dan SpinozaDear xCloud Team, I have been using xCloud for some time now and am genuinely impressed with its capabilities and the flexibility it offers by allowing users to bring their own VPS for management. It's a fantastic service, and my experience so far has been very positive. Successful migrated 5 sites on a single server. Xcloud migration tool worked great. There were few hiccups with security plugin like MalCare but disabling the plugin prior to migration worked just fine.
Rahil MaknojiaCame from runcloud. Tried xcloud and never came back.
Karl FanegaHow Advanced Web Strategies Saved Over $2,000 & Recovered 56 Hours per Month Managing 70+ Client Websites
Gary MoodyxCloud gave me what no other hosting platform could: the flexibility of a VPS with the convenience of managed WordPress. As a solo founder running an entire business on one server, that combination is an important unfair advantage.
Jorge de los Reyes MartínezI use Server Avatar and xCloud and I'll sooner use xCloud than Server Avatar personally.
Jay PaganoHow Newman Web Solutions Ensured Perfect Uptime and Seamless Scaling For 120+ WordPress Sites with xCloud
Lori NewmanI too have moved over to xCloud. It's pretty sweet. One click n8n and uptime Kuma apps
John ApertureI went from Cloudways to xCloud. No intention on switching in the foreseeable future.
Blaine MooreFrequently Asked Questions
Short answers about running your own LLM on xCloud.
What is a self-hosted LLM?
It is a large language model that runs on a server you control, instead of a provider's API. You download an open model with a tool such as Ollama, and your apps or chat screen talk to it on your own server.
How much RAM do I need to self-host an LLM?
Plan for at least 20 to 30 percent more RAM than the model's size, plus room for the operating system and other apps. For example, a 4.4 GB model needs at least 5.8 GB of RAM by the 30 percent rule.
Do I need a GPU?
Not to start. Ollama runs on CPU, but CPU is slower than a GPU, and xCloud's guide recommends a GPU server for the best speed. Our Cloud VPS sizes run on CPU, so connect your own GPU machine if you need one.
Which models can I run?
You choose from the list in Ollama → Management, which includes open models such as Llama, Gemma, Qwen, Mistral and DeepSeek. xCloud does not promise that a given model runs well on a given server. The main limit is whether it fits in memory.
How fast will my model run?
It depends on the model and your hardware, and xCloud has not measured speeds on its server sizes, so we can't give you speed figures. Try your model on a small test before you size up.
Is a self-hosted LLM private?
Prompts sent to a local model stay on your server. If you connect a hosted provider in a chat app, those chats go to that provider. Models marked Cloud run on Ollama's servers, so those prompts leave your server. Apps on other servers can't reach Ollama until you change your server's NGINX settings. Ollama has no login of its own, so restrict who can reach it before you make that change. OpenWebUI and LibreChat on the same server still reach it privately.
Which chat app should I choose?
Choose OpenWebUI for a team chat screen, LibreChat to mix local and hosted models, AnythingLLM to chat with your documents, or Hollama for a minimal screen. All of them need a model server such as Ollama or a hosted provider. OpenWebUI and LibreChat on the same server can reach Ollama through Enable Ollama. We have not tested AnythingLLM or Hollama with an Ollama site on xCloud. Ollama is closed to other apps by default, and it has no login. Hollama may need extra setup, and it may mean opening Ollama to the internet.
Can I use my own server?
Yes. Connect a server from your provider and install the same apps. You pay your provider for the server. xCloud's self-managed plan is free for 1 server and 10 sites, and each paid server is billed at a volume rate. The Free plan cannot install Ollama, OpenWebUI or LibreChat, so use a paid server for them.
Who handles backups and updates?
You do. Nothing upgrades on its own, and app backups run on the schedule you set up. You decide when to update Ollama or a model, and model files stay on the server's disk between restarts.
Can I cancel anytime?
Yes. There is no lock-in, so you can cancel any time. Hosting is billed monthly and charged for what you actually use, so when you delete the server the unused balance is refunded to your account, less up to 10% in payment-processing fees.
Run Your Own AI Model on xCloud
Start with Ollama and a small model, then add a chat screen for your team.