How to Run Local Models in Claude Desktop

Step-by-step guide to connecting Ollama’s local models to Claude Desktop via the gateway — no API costs, no cloud, runs fully offline.

Claude Desktop has a third-party inference feature that lets you replace Anthropic’s API with any model provider, including a local AI model running entirely on your machine.

This guide walks you through the full setup: install Ollama, download a model, configure the gateway in Claude Desktop, and start a local conversation.

Everything done within 10 minutes.

What’s in this guide

• What you’re setting up (Ollama + Claude Desktop)

• Step 1: Install Ollama

• Step 2: Pick a model

• Step 3: Download your model

• Step 4: Confirm Ollama is running

• Step 5: Test the model (optional)

• Step 6: Enable Developer Mode

• Step 7: Configure the gateway

• Step 8: Sign in and fix errors

• Step 9: Use the Code tab

• Step 10: Start a conversation

• Things to know

Hi, I’m Jenny 👋
I build AI systems and tools, then share how I did it. I run the Practical AI Builder program, for people who already use AI and want to build real things with it. Check it out if that sounds like you.

If you’re new to Build to Launch, welcome! Here’s what you might enjoy:

• Claude master hub

• 15 Claude Projects with prompts to get you started