Switching my local LLM to Qwen 3.6, a 35B Mixture-of-Experts model, on a 16 GB GPU

This site does not allow itself to be embedded. You can still read it on the original site — the toolbar below keeps your place in the directory.

Qwen3.6-35B-A3B fits on a 16 GB card with llama.cpp's `--n-cpu-moe`. Disabling thinking mode needed both reasoning-budget 0 and enable_thinking=false.

Read on paulsprogrammingnotes.com ↗