- Qwen (quen3:8b): an LLM with 8 billion learned parameters in memory. Executing directly on the CPU/GPU inside your machine. No cloud server is involved once the model is downloaded.
- Ollama: software that makes it easy to download, run, and manage AI models locally on your computer.
brew install ollama
ollama --versionDownload and run Qwen
Note This will allow you to run in terminal but will not be able to edit/create files.
ollama run qwen3:8bList models
ollama listRemove model
ollama rm qwen3:8bInstall Continue extension.
In VScode, Cmd+Shift+P -> Continue: Open Settings -> Configs -> Main Config
name: local
version: 1.0.0
schema: v1
models:
- name: qwen
provider: ollama
model: qwen3:8b
context:
- provider: code... should save as ~/.continue/config.yaml