Local AI with Ollama + Open WebUI

Introduction

This guide installs Ollama on Linux or Windows (via WSL), pulls and runs models, including general-purpose models like Llama 3 and reasoning models like DeepSeek, and stands up Open WebUI via Docker for a browser-based interface. One setup, multiple model families.

Think of it like keeping a personal assistant in your own house instead of phoning a call center. Everything you tell it stays under your roof, nobody else is listening in.

1) Install Ollama

Get Ollama ↗

Linux: use the install script below.
Windows: install the native app, or enable WSL and follow the Linux steps inside WSL.

1a) Windows: Enable WSL (One-Time)

$wsl --install

Reboot if prompted. Then open Terminal and run wsl to enter your Linux distro shell.

1b) Update your Linux environment

$sudo apt update
$sudo apt upgrade -y

1c) Install Ollama (Linux/WSL)

$curl -fsSL https://ollama.com/install.sh | sh

1d) Verify Ollama is running

Open: http://localhost:11434

You should see "Ollama is running".

2) Pull & Run General-Purpose Models

Pull Llama 3 (Meta):

$ollama pull llama3

Or pull and run immediately:

$ollama run llama3

Model libraries:

Ollama Library Hugging Face

3) Pull & Run DeepSeek Models

Ollama exposes DeepSeek variants in its library. Pull one (replace with your preferred variant if needed):

$ollama pull deepseek-r1:latest

Then run it:

$ollama run deepseek-r1

Tip: list available models and tags in the Ollama Library.

4) Web UI with Docker (Open WebUI)

4a) Install Docker Engine (Ubuntu)

sudo apt-get update
sudo apt-get install -y ca-certificates curl
sudo install -m 0755 -d /etc/apt/keyrings
sudo curl -fsSL https://download.docker.com/linux/ubuntu/gpg -o /etc/apt/keyrings/docker.asc
sudo chmod a+r /etc/apt/keyrings/docker.asc

echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] \
https://download.docker.com/linux/ubuntu $(. /etc/os-release && echo "$VERSION_CODENAME") stable" | \
sudo tee /etc/apt/sources.list.d/docker.list > /dev/null

sudo apt-get update
sudo apt-get install -y docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin

4b) Run Open WebUI container

Connects to your local Ollama at http://127.0.0.1:11434 and exposes the UI on port 8080:

$sudo docker run -d --network=host -v open-webui:/app/backend/data -e OLLAMA_BASE_URL=http://127.0.0.1:11434 --name open-webui --restart always ghcr.io/open-webui/open-webui:main

4c) Verify container

$sudo docker ps

4d) Open the Web UI

Open WebUI (http://localhost:8080) ↗

First user you create becomes the SuperAdmin, store those credentials safely.

5) Add More Models to Open WebUI

Pull additional models with Ollama (replace {ai-model}):

$ollama pull {ai-model}

6) Fine-Tune / Create Custom Models

In Open WebUI, go to Workspace.
Click Create a model.
Name your model and set a tag.
Add a description and set model params to define behavior.

Wrap-up

One Ollama + Open WebUI setup covers both general-purpose models (Llama 3) and reasoning models (DeepSeek), swap models with ollama pull, no need to rebuild the stack per model family.