Join the waitlist

Ollama (Local Models)

Run AI models locally on your machine — completely free, fully offline.

What Is Ollama?

Ollama is an app that lets you run open-source AI models locally on your computer. No API key, no usage costs, no internet required.

Install Ollama

  1. Download Ollama from ollama.ai
  2. Install and open it (it runs in the background)
  3. Open Terminal and run: ollama pull qwen3.5:9b to download a model.
    (replace qwen3.5:9b with the model you want to use. See Recommended Models for more information.)

Configure in Continuum Writer

On first launch

  1. Choose Ollama as your AI provider in the setup wizard
  2. The base URL defaults to localhost:11434 — change this only if you've configured Ollama differently
  3. Click "Save & Test Connection" — the app will detect available models
  4. Select a model from the dropdown
  5. Click Next to continue

From the settings menu

  1. Open Settings (gear icon, bottom-left)
  2. Under AI Provider, select Ollama
  3. The base URL defaults to localhost:11434 — change this only if you've configured Ollama differently
  4. Click "Test Connection" — the app will detect available models
  5. Select a model from the dropdown

Hardware Requirements

  • Minimum: 16GB RAM — will run smaller models (7B parameters)
  • Recommended: 32GB+ RAM — for better quality models
  • PC with GPU: Significantly faster inference with a dedicated NVIDIA GPU

Performance Note

Local models are slower than cloud providers, especially on Mac. Expect responses to take 30-90 seconds depending on your hardware and the model size. For the fastest experience, use a cloud provider (OpenAI or Anthropic).

Recommended Models

The app uses three model roles. For the Chat Model, use a capable model that supports tool use (e.g. qwen3.5:9b or qwen3.5:27b depending on your hardware). For the Router and Summarise models, a smaller model like qwen3.5:4b works well.

If your machine struggles with larger local models, Ollama also offers cloud-hosted models (like Kimi K2, DeepSeek, and Gemma 4) that don't require powerful hardware.

See Recommended Models for a full comparison and hardware guidelines.