How to configure Continue.dev with Ollama

What this does

Connects the Continue.dev sidebar to a local Ollama instance so code completions and chat responses route through locally hosted models. After completion, Continue uses Ollama as the default backend.

Steps

1. Open the Continue config file. Click the gear icon in the Continue sidebar, or open ~/.continue/config.json directly in VS Code.

2. Add an Ollama model entry. Insert a model configuration block within the models array. Replace MODEL_NAME with a model present locally.

   {
     "title": "Ollama",
     "provider": "ollama",
     "model": "MODEL_NAME"
   }
   

3. Set the default model. Ensure the newly added Ollama entry is the first item in the models array.

4. Configure the base URL if non-default. If Ollama listens on a different port, add "apiBase": "http://localhost:11434" explicitly.

5. Save and reload. Save the config file. The Continue sidebar reloads and begins routing requests to Ollama.

Verification

curl -s http://localhost:11434/api/tags | head -c 200
# Expected: JSON object listing available models

Common failures

• Model not found error — The model name in config does not match an installed model. Run ollama list and use the exact name.
• Connection refused on port 11434 — Ollama is not running. Start it with ollama serve.
• Timeout on first request — Large models take time to load into VRAM. Wait 30-60 seconds.
• Stale config cached — Run "Developer: Reload Window" after saving changes.
• Wrong base URL — Docker port mapping may change the address. Verify with curl.

Operator checkpoint

Before treating this as solved, write down the local runtime, model or package version, hardware/backend if relevant, and the verification output. This keeps the guide useful as a Will-It-Run style decision instead of a one-off command transcript.

Related guides

• How to install Continue.dev in VS Code
• How to set up Continue.dev with LM Studio
• Course Local AI Fundamentals