06:59
2026-07-04
maloyan.xyz
large-language-models
Running Qwen 3.6 Locally on a Mac Mini M4 with 16GB RAM
Qwen open-sourced the 35-billion parameter Mixture of Experts model Qwen 3.6-35B-A3B, which activates only 3 billion parameters per token and runs on a $599 Mac Mini M4 with 16GB RAM at 17 tok/s with …