Skip to main content

WorkBuddy Ollama Local Deployment

Installing Ollama (Local Model Runtime Tool)​

Step 1: Download and install

Visit the official website: https://ollama.com/

Click Download → select Windows

After the download completes, double-click the installer and follow the prompts all the way through

Once installation is complete, Ollama will run automatically in the background (an icon is visible in the system tray)

Step 2: Verify the installation

Press Win + R, type cmd, open the command line, and run:

ollama --version

If you see the version number output, the installation was successful

Downloading a Local Model​

Pull the model (using qwen3:4b as an example):

ollama pull qwen3:4b

After the pull completes, test it:

ollama run qwen3:4b "Hello, introduce yourself"

If you see the model's response, everything is working properly

Configuring Ollama in WorkBuddy​

Step 1: Open the model configuration

Open the WorkBuddy client

Click the avatar/username in the bottom-left corner → go to Settings

Find the Models tab

image

Step 2: Add the Ollama local model

Click Add Model / Custom Model

For the type, select: Local Deployment (Ollama)

For the API endpoint, enter: http://localhost:11434

For the model name, enter: qwen3:4b (must match the name of the model you pulled)

Click Save

image

Step 3: Switch and use

Once configured, select the qwen3:4b (Ollama) you configured in the model selector of the WorkBuddy chat interface to start offline conversations!