Skip to article frontmatterSkip to article content
Site not loading correctly?

This may be due to an incorrect BASE_URL configuration. See the MyST Documentation for reference.

While local models work well for Chat, Edits, and Agent Mode, GitHub Copilot’s real-time inline ghost-text autocompletion relies on custom, specialized models trained for ultra-fast response times. Local LLMs configured via (BYOK/BYOM) are generally limited to the Chat/Agent APIs rather than replacing the real-time completion engine.

VSCode extension for Continue

If you want 100% offline inline completions + chat using local models, popular dedicated open-source extensions like Continue are often preferred.

🛠️ How to set it up...

  1. Install Continue VSCode extension.

  2. Add the following lines to Continue’s main YAML config file:

models:
  - name: Qwen3.5
    provider: openai
    model: qwen3.5:4b-q4_K_M
    apiBase: http://localhost:12434/engines/v1
    roles:
      - chat
      - edit
      - apply
      - autocomplete
General Interest Webinar
Bring Your Own Model