Recommended models

Three tiers based on your available RAM and quality needs.

Tips for code generation

1 Use Q6_K or higher for code — Q4 quantization can introduce subtle logic errors

2 Pair with a local tool-use setup (Aider, Continue) for file-aware editing

3 Close Chrome and Docker before loading large coding models to free RAM

4 For simple completions, a 9B model is fast and accurate enough — save large models for complex tasks

Related Pages

Find the right model for your Mac

DevPulse monitors your actual RAM usage and tells you exactly which models will run alongside your dev tools.

Download for macOS

macOS 14+ · Apple Silicon & Intel · Free during launch