SetuprollSetuproll
A
Continue logoContinuePrivate coding chat on Apple Silicon

Mac Local Model Daily Driver

Setuproll editorial@setuproll
84.0Overall score

Runs a capable open model fully offline on a MacBook and wires it into VS Code for chat and autocomplete. For developers under strict data rules who refuse to send source code to any cloud provider.

84.0Score
4Components

Install this build

Export
terminal
brew install ollama && ollama pull qwen3-coder:30b

Components

Model

  • Qwen3 Coder 30B (Q4_K_M)
  • Qwen2.5 Coder 1.5B for autocomplete

Stack

  • Ollama (Metal backend)
  • Continue extension

Hardware

  • M-series, 32GB+ unified memory

How it works

  • Install Ollama and pull a coder model sized to your memory
  • Add it to Continue as the chat and autocomplete provider
  • Edit and refactor with full repo context, fully offline

Summary

Runs a capable open model fully offline on a MacBook and wires it into VS Code for chat and autocomplete. For developers under strict data rules who refuse to send source code to any cloud provider.

84.0 score

0 Reviews

Your rating
Sign in to post

Loading discussion...

← All builds