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

Description and use

Local LLMs on an M3 MacBook Pro work well for small, focused coding tasks but are too slow for medium‑complexity projects that require an agentic workflow. Gemma 4 31B‑MLX offered the best local experience, yet overall latency still fell short of cloud assistants.

Problem

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

Outcome

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.

Workflow

• 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

Evidence

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

Source

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.

Source