Qwen 3.6 27B is the sweet spot for local development
Piotr Migdał tested Qwen 3.6 27B and calls it the first local model that works as a general intelligence. Running 8-bit quantized on a Macbook Max M5 128GB with llama.cpp and multi-token prediction, it hits 32 tok/s using 42GB RAM. It handled constrained writing, generated a hexagonal minesweeper npm package in one shot, and built a reactive landing page. The post includes full llama.cpp setup commands and recommends against Ollama on ethical grounds.
Why it matters: Piotr Migdał benchmarked an 8-bit quantized Qwen 3.6 27B on a MacBook Max M5 128GB, reporting 32 tokens per second at 42GB memory, plus a hex minesweeper npm package and a responsive landing page.