June 2026

AI
2026-06-08 14:29 (6 days ago)
Running Local LLMs on an M4 Mac mini 16GB — Practical Options and Limits

Run Qwen3.5-9B locally on an M4 Mac mini 16GB with the right model and runtime choices. Includes setup steps and fixes for common pitfalls around `thinking`, `presence_penalty`, and `num_predict`.

Categories

Archive