- Coding
- Intermediate
A fully offline coding assistant in VS Code
Connect the Continue extension to a local Ollama model so completions and chat never leave your machine — great when company code can't go to the cloud.
- Models
- qwen2.5-coder
- Tools
- Ollama, Continue, VS Code
- VRAM / RAM
- 16GB recommended
- Platforms
- Mac, NVIDIA
- Original source
- docs.continue.dev
Sample entry.
Approach
- Use a larger model (e.g. 14B) for chat and a small one (1.5B–3B) for inline completion to balance quality and speed
- In Continue’s config set the provider to
ollamaand pick separate chat and autocomplete models
Notes
Smaller completion models mean lower latency. If VRAM is tight, keep completion snappy and let chat be slower.