Book a demo
Book a demo
Login

LlamaGPT Hosting Live In 5 Minutes

Deploy LlamaGPT hosting and give yourself a private Llama 2 chatbot on your own domain. xCloud runs the pinned LlamaGPT 1.0.1 images with the Llama 2 7B model already bundled, keeps the model server on a private network, puts a sign-in prompt with a generated password in front of the site and publishes it over HTTPS — prompts and answers are processed on your server, with no API keys and no per-token fees.

Deploy your LlamaGPT
  • No terminal
  • No technical skills needed
  • No lock-in, cancel anytime

What is LlamaGPT?

LlamaGPT is a self-hosted, offline, ChatGPT-like chatbot powered by Llama 2, from the Umbrel team. Its chat interface talks to an OpenAI-compatible model server that runs a Llama 2 7B chat model on your own hardware.

This template bundles the model in the image and runs it on the server CPU, so there are no API keys and no per-token fees. Prompts and answers are processed on your server rather than sent to a third-party AI service.

From Sign-Up to a Live Chatbot In Just 3 Easy Steps

A self-hosted Llama 2 chatbot normally means pulling a multi-gigabyte model, wiring a chat interface to a model server, adding authentication, a domain and a certificate. This is the same result without assembling any of it.

  1. Step 01

    Sign Up

    Create your xCloud account and pick LlamaGPT from the OneClick catalog. Choose your domain, then set a username and password for the sign-in prompt — a strong password is generated by default.

  2. Step 02

    We Deploy It For You

    One click. We bring up the pinned LlamaGPT images: the llama-gpt-api model server with the Llama 2 7B model baked in, the llama-gpt-ui chat interface, and a gateway that asks for your username and password. Only the gateway is published, over HTTPS on your domain; the model server and interface stay on the private network. Allow roughly 5 minutes for the first start while the model loads.

  3. Step 03

    Send Your First Prompt

    Open your HTTPS LlamaGPT URL, sign in with the saved credentials when the browser asks, then type a prompt in the chat box. Expect a few seconds for a short answer — generation runs on the server CPU.

Everything LlamaGPT Does, On Your Own Server

LlamaGPT runs in full here: a ChatGPT-style interface in front of a Llama 2 7B model on your own server, behind a sign-in prompt.

  • A ChatGPT-Style Interface

    Chat with the model in a familiar conversation layout, with your conversations kept in your browser.

  • Llama 2 7B Bundled

    The model ships inside the image, so there is no separate download step and no API key to obtain.

  • Runs On Your CPU

    Generation is CPU-only — about 6 tokens per second measured on a 6-core server. A GPU is not used.

  • Private By Design

    Prompts and answers are processed on your server, and the template makes no calls to third-party AI APIs.

  • Sign-In In Front Of Everything

    HTTP Basic authentication guards the whole site, so others cannot use your server CPU; requests without valid credentials get a 401.

  • An OpenAI-Compatible Model Server

    The llama-gpt-api service is an OpenAI-compatible server (llama.cpp), reachable only on the install's private network.

Everything You Need To Run Your Private Chatbot 24/7

Managed hosting for LlamaGPT, so the parts that keep it online are not your problem.

  • LlamaGPT 1.0.1 deployed instantly
  • Official images pinned by digest
  • Sign-in password generated for you
  • Model server kept off the public internet
  • Free SSL certificate
  • Server backups and snapshots
  • Server security updates included
  • 30+ server locations
  • Unused balance refunded

What You Can Do With LlamaGPT

  • A private chatbot for sensitive prompts

    Ask questions and draft text with a model whose prompts and answers stay on your own server instead of a third-party AI service.

  • Chat without API keys or per-token fees

    The model is bundled in the image, so there is no account to create with an AI provider and nothing is billed per token.

  • An offline-capable Llama 2 sandbox

    Try a Llama 2 7B chat model through a ChatGPT-style interface without wiring a model server to a front end yourself.

  • A shared chatbot behind one sign-in

    Give a small group a single username and password for the whole site, so only people you trust can use your server CPU.

LlamaGPT Screenshots

LlamaGPT chat interface with a prompt typed into the message box
LlamaGPT chat interface showing the model's reply to a prompt

LlamaGPT vs Alternatives

ChatGPT
OpenAI's hosted chat service. LlamaGPT is the self-hosted option: the model runs on your own server and prompts are not sent to a third party.
Ollama
A self-hosted runtime for open-source AI models that you manage from one place; LlamaGPT instead ships one bundled Llama 2 7B model with its own chat interface.
Open WebUI
A customizable web interface that connects to Ollama and any OpenAI-compatible API endpoint; LlamaGPT bundles its own model server and model.

Simple Pricing. Everything Included.

Dedicated Cloud VPS sizes, pre-configured for LlamaGPT hosting. Pick the one that fits, and resize any time.

Cloud VPS 16 GB

Most popular

Covers the template's 8 GB RAM minimum for a private Llama 2 chatbot.

$59.99per month

  • 16 GB RAM
  • 6 vCPU cores
  • 200 GB NVMe SSD
  • 30 TB
  • Unlimited
Get started

Every size is a dedicated Cloud VPS we provision, patch, monitor and restore. Billed monthly with no lock-in — delete the server and the unused balance comes back to your account. LlamaGPT's code is MIT-licensed; the bundled Llama 2 weights carry their own licence.

Docker hosting

Already Have a Server? Bring Your Own

Connect any VPS — DigitalOcean, Vultr, Linode, AWS, Hetzner or bare metal — and deploy LlamaGPT on it through the same panel, for a per-server management fee instead of a Cloud VPS rental.

Free

Start your journey without cost.

$0forever

  • 1 server
  • 10 sites
Start free

Starter

Most popular

Your rate with 2–5 servers connected.

$5per server / month

  • 2–5 servers
  • Unlimited sites
  • All features included
  • Bring any VPS provider
Get started

Professional

The same platform, discounted at 6–10 servers.

$4per server / month

  • 6–10 servers
  • Unlimited sites
  • All features included
  • Bring any VPS provider
Get started

Agency

The same platform, discounted at 11+ servers.

$3per server / month

  • 11+ servers
  • Unlimited sites
  • All features included
  • Bring any VPS provider
Get started

Priced per connected server, so your rate adjusts automatically as you add or remove servers. You pay your own provider for the server itself.

Self-managed hosting

Ready To Run Your Own Private Chatbot?

LlamaGPT on xCloud runs on a dedicated Cloud VPS that we provision, patch, monitor and restore. Deploy faster. Own the server. Stay in control.

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 Geovanny
I'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 Pineda
I'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 Koo
How Cloud Nine Web Elevated Client Experience While Streamlining Hosting Operations using xCloud
Ed Ellingham
xCloud 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 Butucel
xCloud isn't just a solution. It's like one of that friend who got your back when you screw things up pretty bad.
Waqar Ahmed
Trust 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 Singh
So 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 Villa
Came from cloudways then to runcloud then to xcloud. Looks like I'm staying here.
Gerson El
I'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 Lewis
I came from Cloudways and won't go back. Highly impressed with xCloud. Glad I gave them a chance.
Jared McDowell
I 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 McCan
How Kevin Heinrichs Cut Hosting Costs by 84% While Running WooCommerce & Node.js Sites Efficiently
Kevin Heinrichs
I had 150 sites on cloudways and am in the process of moving them to xcloud. Much faster and better priced.
Dan Spinoza
Dear 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 Maknojia
Came from runcloud. Tried xcloud and never came back.
Karl Fanega
How Advanced Web Strategies Saved Over $2,000 & Recovered 56 Hours per Month Managing 70+ Client Websites
Gary Moody
xCloud 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 Martínez
I use Server Avatar and xCloud and I'll sooner use xCloud than Server Avatar personally.
Jay Pagano
How Newman Web Solutions Ensured Perfect Uptime and Seamless Scaling For 120+ WordPress Sites with xCloud
Lori Newman
I too have moved over to xCloud. It's pretty sweet. One click n8n and uptime Kuma apps
John Aperture
I went from Cloudways to xCloud. No intention on switching in the foreseeable future.
Blaine Moore

Frequently Asked Questions

Feel free to contact us with any questions or concerns you may have.

Is my data sent to OpenAI or anyone else?

No. The model runs on your server and the template makes no calls to third-party AI APIs.

How do I sign in?

The browser asks for the username and password you set at install, shown in the installation credentials. LlamaGPT has no accounts of its own; this prompt guards the whole site, and requests without or with wrong credentials get a 401.

How fast is it?

CPU-only: about 6 tokens per second measured on a 6-core server. A GPU is not used, so a short answer takes a few seconds and a long one can take a minute or more.

Why does the site not respond right after install or a restart?

On every start the model loads into memory, which takes up to about 5 minutes. Until then the page may not respond; give it time before restarting anything.

Where are my chats stored?

In your browser's local storage, not on the server, so they are not shared across browsers or devices and clearing site data removes them.

Which model does it run?

A Llama 2 7B chat model, bundled in the image. The model name and path are set in the environment file and are not meant to be changed.

What runs alongside LlamaGPT?

A llama-gpt-api model server and a llama-gpt-ui chat interface, both on the install's private network with no host ports, plus the gateway that publishes the site over HTTPS and asks for your username and password.

How do I change the username or password?

Rotate them in the environment settings, then Restart.

Edit environment variables

What should I back up?

Nothing on the server: the model ships in the image and chat history lives in each visitor's browser.

Does xCloud automatically back up or update LlamaGPT?

No. The template pins LlamaGPT 1.0.1 by immutable digest; new installations use the pinned release and existing sites are not automatically upgraded. Read the upstream release notes, then bump the readable tag and digest together on your own schedule. Server-level backups and snapshots are available on every Cloud VPS.

What are the server requirements, and why does this page sell 16 GB?

The template's baseline asks for 4 CPU cores, 8192 MB of RAM and 12 GB of disk. Measured idle use in QA was about 294 MiB and about 880 MiB after a chat, plus the memory-mapped 3.8 GB model — roughly a 5 GB working set in total. This page sells the 16 GB tier because the manifest's 8 GB floor needs more than the 6 GB entry rung.

What survives a restart?

The bundled model is still in place after an xCloud Restart with no re-download, and the chat answers again once the model has loaded.

What licence applies?

The LlamaGPT code is MIT. The bundled Llama 2 weights are under the Llama 2 community licence and the model's own terms.

Can I cancel anytime?

Yes. There is no lock-in — 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.

Related apps

Other AI apps people run on the same kind of server.

Related resources

The environment and HTTPS guides that matter most once LlamaGPT is live.

More AI apps in one click

Browse all one-click apps →

Ready to Run Your Own Private Chatbot?

Connect your first server in minutes. No credit card required, and no plan you have to grow into.

Deploy LlamaGPT now