Self-hosted AI on a VPS: the complete series

The hub for the self-hosted AI series.

This series explains how to run AI tools on your own server, for beginners. It starts with what self-hosted AI is and what it can realistically do, walks through your first setup, shows what fits on each plan size, and then covers useful projects: searching your own documents, automating work, speech, and AI agents that carry out tasks for you. It finishes with how to keep all of it safe and private.

The honest summary before you start: small AI models on a VPS are slower and less capable than the big hosted services, and the large models need far more memory than most plans have. Self-hosting shines for privacy, for always-on tools and agents, and for learning. Many setups mix both, running the tools on your server and calling a hosted model through an API for the hard thinking.

4 GB to 8 GB VPS plans in stock, the sweet spot for self-hosted AI

In stock when this page loaded. See all 9 matching plans

What is in this guide

The parts of the series

PartGuideWhat it covers
1Self-Hosting AI Explained for BeginnersWhat self-hosted AI is, what it is good for, and its honest limits
2Self-Hosted AI Tools Explained: A Beginner's MapThe main kinds of tools and how they fit together
3Your First Self-Hosted AI in 15 MinutesA first working setup, step by step
4What AI Can You Run on a 1-2 GB VPS?What fits on small plans, mostly tools that call an API
5What AI Can You Run on a 4 GB VPS?Small local models and comfortable AI apps
6What AI Can You Run on a 6-8 GB VPS?Larger local models and several AI tools together
7What AI Can You Run on a Dedicated Server?When a whole machine makes sense for AI
8Self-Hosted AI vs Paying for an API: What It Really CostsComparing server costs with pay-per-use model services
9Search and Question Your Own Documents With a Private AI (RAG Explained)Asking questions about your own files
10Automate Your Work With AI: n8n Workflows on a Small VPSWorkflows with AI steps that run on their own
11Transcribe and Speak: Self-Hosted Speech AI on a VPSTurning speech into text and text into speech
12Keeping Your Self-Hosted AI Safe and PrivateSecurity and privacy for every AI tool in the series
13Running a self-hosted AI agent on a VPSAgents such as OpenClaw and Hermes Agent that carry out tasks for you, and how to run them safely

Where to start

  • You are new to all of this. Read parts 1 and 2, then try part 3.
  • You want to know what your plan can run. Go to the part for your plan size: 4, 5, 6 or 7.
  • You are deciding whether it is worth it. Read part 8 before buying anything.
  • You have a project in mind. Documents: part 9. Automation: part 10. Speech: part 11. An assistant that does things for you: part 13.
  • You already run AI tools. Read part 12, and part 13's security rules if you run an agent.
  • You have never set up a server. Start with your first hour on a new RackNerd VPS.

A few words you will see

TermWhat it means
ModelThe AI itself. Larger models are more capable and need more memory.
Local modelA model that runs on your own server.
APIA way to use a hosted model over the internet, billed by use.
QuantisedA model shrunk to use less memory, with some loss of quality.
RAGRetrieval-augmented generation: letting a model answer from your own documents.
AgentAn AI that plans and carries out tasks using tools, not just answers questions.
OllamaA popular tool for running local models.

Which plan for which job

A rough starting point, not a promise. Memory needs vary a lot with the model, the settings and the tool. The part guides give more detail.

JobA sensible starting planRead
A chat interface using a hosted model through an API1 GB to 2 GBPart 4
Workflows with AI steps, using an API2 GBPart 10
A light AI agent such as Hermes Agent, using an API2 GB to 4 GBPart 13
A small local model for simple tasks4 GBPart 5
Questions about your own documents4 GB with an API, more with a local modelPart 9
Speech to text for short recordings4 GBPart 11
OpenClaw, or any agent that drives a browser8 GBPart 13
Larger local models, or several AI tools together6 GB to 8 GBPart 6
Bigger models and heavy useA dedicated serverPart 7

RackNerd's control panel can install some of these tools in one click, including Ollama, AnythingLLM, LibreChat, n8n, OpenClaw and Hermes Agent. A one-click install erases the server first. RackNerd's one-click apps explained covers what each one does and how to secure it.

2 GB VPS plans in stock, enough for AI tools that use an API

In stock when this page loaded. See every plan

Local model or API?

Local model on your VPSHosted model through an API
PrivacyYour data stays on your serverYour prompts go to the model provider
QualitySmaller models, simpler tasksThe most capable models
Speed on a VPSSlow on CPU, especially longer answersFast
CostThe server, which needs more memoryA small server, plus pay-per-use model charges
Best forPrivate, simple tasks and learningHard tasks, agents and anything that needs quality

Part 8 works through the costs. Whichever you choose, set a spending limit on any API account before you start.

Six rules for every AI project

  1. Keep control panels private. Bind AI tools to 127.0.0.1 and reach them through an SSH tunnel or VPN. See setting up a WireGuard VPN.
  2. Never leave a tool without a login, and turn off open sign-up.
  3. Protect API keys. Keep them in files readable only by the app, with a spending cap on each.
  4. Give agents their own server and only the tools they need. See part 13.
  5. Read and test anything AI writes before you rely on it.
  6. Check licences. Models and tools have their own terms, especially for business use.

Part 12 and a beginner's guide to securing your VPS cover the rest.

What this series does not cover

  • Training your own models. That needs graphics cards and far more resources than a VPS.
  • Graphics card servers. RackNerd's VPS plans run on CPU. Local models are therefore slower than on a machine with a suitable graphics card.
  • Exact model recommendations. Models change every few months. The guides describe families and sizes, and you should check each project's current documentation.
  • Guarantees of speed or quality. Test with your own tasks.

Cautions for every plan: swap is a safety net and not extra RAM, unmetered does not mean unlimited, fair-use limits apply to CPU and bandwidth, and RackNerd's acceptable use policy covers what your AI tools do.

When to step up

If a local model is too slow or keeps running out of memory, either move up a plan size or switch that task to an API. For agents, 8 GB gives room for browser tasks. For larger local models and heavy use, a dedicated server is the next step. How to read VPS specs explains which specs matter for AI.

8 GB VPS plans in stock, for agents and larger local models

In stock when this page loaded. See every plan

Dedicated servers in stock with the most memory, for bigger models

In stock when this page loaded. See all 71 matching plans

To compare what is available now, start with the cheapest RackNerd VPS guide and check the sales page.

More RackNerd guides