I Tried Local LLMs for Coding on My M3 MacBook Pro: What Worked and What Didn't

说明与用途

在M3 MacBook Pro上运行本地LLM可满足小型代码任务，但在需要代理式工作流程的中等复杂项目中速度过慢。Gemma 4 31B‑MLX表现最佳，但整体延迟仍低于云端助手。

问题

Can a local LLM become a practical everyday coding assistant on a laptop?

结果

Local LLMs on an M3 MacBook Pro can serve as a useful coding assistant for small, focused tasks, but their latency in agentic, repository‑wide workflows limits productivity for medium‑complexity projects. The best local experience was with Gemma 4 31B‑MLX, yet overall speed remained insufficient compared to cloud assistants.

工作流

• Set up Ollama on M3 MacBook Pro and bind to 0.0.0.0:11434
• Configure VS Code on Lenovo to point to Mac’s IP
• Test network connectivity with curl to /api/tags
• Run and switch models with ollama run <model>
• Adjust context length via OLLAMA_CONTEXT_LENGTH
• Evaluate models (Gemma 4 26B, Gemma 4 26B‑MLX, Qwen3‑Coder 30B, Gemma 4 31B‑MLX) for speed and quality
• Use VS Code to ask for explanations, code snippets, refactorings, tests, design ideas
• Attempt agentic workflow: repository inspection, plan generation, edits, build/test feedback
• Measure latency per step and overall loop
• Compare local performance to cloud Copilot
• Decide on tool usage based on workflow needs

证据

Gemma 4 26B worked well on my machine and was capable enough to make local coding feel practical.

来源

For a medium‑complexity project with repeated planning, repository exploration, code changes, and validation, it was too slow for the way I wanted to work.

来源