Ollama is one of the simplest ways to run local AI models from your own computer. Install the app for your operating system, open a terminal, run a small model first, and then decide whether you want to add a browser interface like Open WebUI later.
The fastest beginner path is:
- Install Ollama for your operating system.
- Open Terminal, PowerShell, or Command Prompt.
- Run a small starter model.
- Confirm that Ollama responds locally.
- Only then move to larger models, Open WebUI, document chat, or custom integrations.
Quick recommendation
Use Ollama if you want a lightweight local model runner, terminal workflow, local API access, or a backend for tools like Open WebUI. Use LM Studio instead if you want a beginner-friendly desktop app for finding, downloading, and chatting with local models through a graphical interface.
If you are new to local AI, do not start by downloading the largest model you can find. Start with a small model, confirm that the setup works, and then move up based on your RAM, VRAM, and patience.
Before you install Ollama
Ollama itself is not usually the hard part. The bigger issues are model size, storage, RAM, VRAM, and expectations.
| Question | Beginner answer |
|---|---|
| Do I need a GPU? | No for very small models, but a GPU or Apple Silicon unified memory usually makes the experience much better. |
| Can I use an 8GB laptop? | Yes for small models and modest expectations. Do not expect large models or heavy PDF workflows to feel smooth. |
| Is 16GB RAM enough? | Usually yes for a practical beginner setup with small or 7B/8B-class models. |
| Does Ollama include a chat app? | The current macOS and Windows app includes chat. The command line and local API remain useful; Open WebUI adds a separate browser interface. |
| Does local mean private? | Local inference can keep prompts on your machine, but model downloads, cloud features, web search, exposed local servers, and third-party tools can change the privacy profile. |
System requirements and storage basics
Use this table as a practical starting point, not as a guarantee that every model will run well.
| Platform | Practical beginner notes |
|---|---|
| Mac | Prefer Apple Silicon for the best beginner experience. Keep enough free disk space for model files. |
| Windows | Ollama runs as a native Windows application and supports NVIDIA and AMD Radeon GPU paths. Windows 10 22H2 or newer is the official Windows requirement. |
| Linux | Ollama provides a Linux install path and can be used as a service-style local runtime. Distribution details vary. |
| Storage | The app is only the start. Downloaded models can take many gigabytes, and a model library can grow quickly. |
| RAM/VRAM | Model size, quantization, and context length determine whether the setup feels usable. |
For Windows, Ollama’s documentation states that the binary install needs at least 4GB of space, with additional space required for large language models that can range from tens to hundreds of gigabytes depending on what you download.
Which first model should you run?
Your first model should be small enough to check that the setup works. Your first model is not your forever model.
| Your machine | First model class to try | What to avoid at first |
|---|---|---|
| 8GB system RAM | Start with a 1B/2B-class model; investigate 3B/4B only if memory allows | Large 13B/14B+ models, long context, multiple apps open |
| 16GB system RAM | Small model or 7B/8B-class model | Assuming every 14B model will be comfortable |
| 32GB system RAM | 7B/8B comfortably; some larger models may be practical | Jumping straight to 70B-class models |
| CPU-only machine | Small model with modest expectations | Treating CPU-only as equivalent to GPU acceleration |
| Windows with NVIDIA GPU | Small model first, then test larger models based on dedicated VRAM | Planning around shared GPU memory as if it were dedicated VRAM |
| Apple Silicon Mac | Small model first; move up based on unified memory | Forgetting that macOS and apps share the same memory pool |
Start with a small or medium model class so setup problems are easier to separate from hardware limits. Do not treat any model fit or speed expectation here as a benchmark result.
Install Ollama on Mac
Ollama currently requires macOS Sonoma (14) or newer. It supports Apple M-series chips with CPU and GPU use; on an Intel Mac, Ollama uses the CPU. Check Apple menu → About This Mac before downloading, especially if your Mac cannot upgrade to Sonoma.
1. Download Ollama
Go to the official Ollama download page and choose the macOS download. Open ollama.dmg, drag Ollama into Applications, and launch it. The app may ask permission to add the ollama command to your PATH; accept that prompt if you want to use the terminal steps below.
2. Open the app
Keep Ollama open while you run the first model. If macOS asks for permission to open the app, follow the normal macOS security prompt.
3. Open Terminal
After the app is installed and running, open Terminal. The command line is where you will run your first model.
4. Check that the command works
Run:
ollama --version
If the command returns a version, the command line is available.
If the command is not found, quit and reopen Terminal. If it still fails, reopen Ollama and check whether its command-link prompt was completed. Ollama's macOS instructions describe that link and the location of the CLI inside the app.
5. Run a small first model
Run a small model first. For example:
ollama run gemma3:4b
Then ask a simple test question:
Explain local AI in one sentence.
If the model replies, the command, model download, and local chat path worked on this Mac. Type /bye to leave the chat.
Model availability note: Starter model names can change. Check the Ollama library before running a command, and choose a small available model if the example model has moved or been renamed.
Install Ollama on Windows
1. Confirm your Windows version
Ollama’s Windows documentation lists Windows 10 22H2 or newer, Home or Pro, as the requirement. If you are using an older Windows build, update before installing. A supported Windows version alone does not establish that your particular GPU has a supported acceleration path; check the Ollama GPU list if acceleration matters to you.
2. Download the Windows installer
Download OllamaSetup.exe from the official Ollama download page.
3. Run the installer
Ollama’s Windows documentation says the installer does not require Administrator rights and installs in your home directory by default.
4. Open PowerShell, Command Prompt, or Windows Terminal
After installation, Ollama should run in the background, and the ollama command should be available in cmd, PowerShell, or your preferred terminal.
Run:
ollama --version
If the command is recognized, continue.
5. Run your first model
Start with a small model:
ollama run gemma3:4b
If this is your first local model download, expect the first run to take longer because Ollama has to download the model before it can run it.
6. Verify the local API if you need it
Ollama’s Windows documentation states that its API is served at:
http://localhost:11434
For most beginners, you do not need to use the API immediately. But if you are setting up Open WebUI or another local tool, this local endpoint is important.
A simple PowerShell test looks like this after gemma3:4b has downloaded:
Invoke-RestMethod -Method POST -ContentType 'application/json' -Body '{"model":"gemma3:4b","prompt":"Say hello in one sentence.","stream":false}' -Uri http://localhost:11434/api/generate | Select-Object -ExpandProperty response
Look for a short answer. If PowerShell reports a connection error, start Ollama and retry ollama list first. If the model is missing, use the download checks.
Install Ollama on Linux
1. Use the official Linux install path
The official Linux installation page gives this installer command for a normal setup:
curl -fsSL https://ollama.com/install.sh | sh
Review the official installer page and use the command only on a computer where you are authorized to install software. If you need a manual installation, ARM64 package, AMD GPU package, or a service-specific setup, follow the corresponding instructions there instead of assuming the same package works everywhere.
2. Confirm the command is available
Run:
ollama --version
3. Run a small first model
Run:
ollama run gemma3:4b
Then ask a short test prompt.
4. Check whether the service is running
If ollama run says the server is unavailable, check systemctl status ollama on a systemd installation and start it with sudo systemctl start ollama if the installed service is stopped. If you installed only the standalone binary, run ollama serve in one terminal and retry the chat in a second terminal. For a service that still fails, read journalctl -e -u ollama and follow the model-load checks. Do not start another server when the port is already in use.
Do you need Docker for Ollama?
Most beginners do not need Docker just to install and use Ollama.
Use the normal app or OS install path first. Consider Docker only if:
- you already use Docker;
- you want an isolated deployment;
- you are following a specific Open WebUI setup that expects containers;
- you are deploying on a server;
- you need repeatable infrastructure rather than a normal desktop install.
If your goal is simply “run my first local AI model,” Docker is usually an unnecessary complication.
Where Ollama stores files
Model storage matters because the app may be small, but the models are not.
| Item | Windows location from Ollama docs | Mac/Linux practical note |
|---|---|---|
| Logs and updates | %LOCALAPPDATA%\Ollama | Check official docs for current paths |
| Binaries | %LOCALAPPDATA%\Programs\Ollama | App or binary path depends on install method |
| Models | %USERPROFILE%\.ollama\models by default | macOS: ~/.ollama/models; normal Linux service: /usr/share/ollama/.ollama/models |
| Temporary files | %TEMP% with ollama* folders | Temporary paths vary |
If your system drive is small, solve storage before downloading several models.
How to move Ollama models to another drive on Windows
Ollama’s Windows documentation says you can change the model location by setting the OLLAMA_MODELS environment variable for your user account.
Beginner-safe outline:
- Create a folder on the target drive, such as
D:\OllamaModels. - Open Windows Settings or Control Panel.
- Search for environment variables.
- Edit environment variables for your user account.
- Create or edit
OLLAMA_MODELS. - Set it to the folder where you want downloaded models stored.
- Quit the Ollama tray app.
- Relaunch Ollama from the Start menu.
- Open a new terminal and run a small model.
If models already exist, the variable does not move them. Follow the complete storage-move guide to copy the model store while Ollama is stopped, check the new location, and reopen a working chat before removing the old copy.
How to verify Ollama is working
Use these checks in order.
| Check | Command or action | Success looks like |
|---|---|---|
| command line exists | ollama --version | Version output appears |
| Model list works | ollama list | A table appears, even if empty |
| Model runs | ollama run gemma3:4b | Model downloads, loads, and replies |
| Local API responds | POST to http://localhost:11434/api/generate | Generated answer appears in the response field |
| Storage is understood | Check model folder | You know where downloaded files live |
Common Ollama install problems
For a missing command, use Ollama command-not-found checks. For a missing or interrupted model download, use model download troubleshooting. If the model is present but will not answer, use Ollama model-load troubleshooting. If a chat works but runs on the CPU when you expected a GPU, use GPU detection checks. These paths begin with the observed failure instead of asking you to reinstall everything.
| Problem | Likely cause | Fix |
|---|---|---|
ollama command not recognized | Terminal was opened before install, PATH not refreshed, or app not launched | Close and reopen the terminal; relaunch Ollama; check the official install notes |
| Windows install uses the wrong drive | Default home-directory install path | Start the installer with a different directory flag or use documented storage settings |
| Models fill the C drive | Downloaded models are much larger than the app | Set OLLAMA_MODELS before building a model library |
| First run takes a long time | Model download is happening before inference | Wait for the download; start with a small model |
| Responses are painfully slow | Model is too large, CPU-only fallback, not enough memory, or long context | Try a smaller model and close other memory-heavy apps |
| Progress symbols look strange on Windows 10 | Terminal font may not render Ollama progress characters correctly | Change terminal font settings |
| Local API does not respond | Ollama background process is not running | Start Ollama, then retry localhost:11434 |
| Open WebUI cannot see Ollama | Container/networking issue or Ollama not reachable from the interface | Finish this install first, then use the Open WebUI with Ollama guide |
| User assumes it is fully private | Local model execution is only one part of the workflow | Read the privacy caveat and avoid cloud-connected features when handling sensitive data |
Privacy notes for Ollama
Ollama can run models locally, and the local API is served from your own machine. But do not treat installation alone as a complete privacy plan.
A local setup can still involve network activity when you:
- download models;
- update the app;
- use hosted cloud models;
- enable web search or other cloud features;
- connect third-party tools;
- expose the local server beyond your own machine;
- use tunnels, proxies, or remote access;
- pair Ollama with an interface that connects to cloud APIs.
The safe beginner assumption is:
A model run locally through Ollama is more private than sending the same prompt to a cloud chatbot, but only the parts of your workflow that actually stay on your machine are local.
Do not expose localhost:11434 to the public internet unless you understand authentication, network binding, firewall rules, and the security consequences.
Should you install Open WebUI next?
Install Open WebUI after Ollama if you want a browser-based chat interface, multi-user-style interface, document workflows, or a more ChatGPT-like front end.
Do not install it immediately if you are still unsure whether Ollama works. First confirm:
ollama --versionworks.ollama run [model]works.- You know where models are stored.
- You have enough disk space.
- You understand that a local interface can still be configured to use cloud providers.
Should you install LM Studio instead?
Install LM Studio instead of Ollama if you want:
- a graphical model browser;
- a desktop chat interface;
- easier first-model discovery;
- built-in document chat;
- a local server only when you need it;
- fewer terminal commands at the start.
Use Ollama if you want:
- a lightweight local runtime;
- command-line model management;
- a local API backend;
- Open WebUI integration;
- developer tooling;
- automation workflows.
What to read next
- Ollama vs LM Studio
- How to Install LM Studio
- Best Local AI Setup for Mac
- Best Local AI Setup for Windows
- How to Install Open WebUI with Ollama
- Chat With PDFs Locally
- Is Local AI Actually Private?
Sources
Sources reviewed for this page:
- Ollama Quickstart: https://docs.ollama.com/quickstart
- Ollama macOS installation: https://docs.ollama.com/macos
- Ollama Windows documentation: https://docs.ollama.com/windows
- Ollama Linux documentation: https://docs.ollama.com/linux
- Ollama Docker documentation: https://docs.ollama.com/docker
- Ollama API documentation: https://docs.ollama.com/api
- Ollama privacy page: https://ollama.com/privacy
- Ollama Gemma 3 4B model entry: https://ollama.com/library/gemma3:4b