@Daniel_Farinax: Qwen3.6-27B on MacBook Pro M5 128GB MLX with custom coding CLI optimized for it. Should also work on M1, M2, M3, M4 Mac…
Summary
Daniel Farinax announces a custom CLI for running Qwen3.6-27B on MacBooks via MLX, seeking beta testers and moving to TypeScript for faster iteration.
View Cached Full Text
Cached at: 05/13/26, 10:25 PM
Qwen3.6-27B on MacBook Pro M5 128GB MLX with custom coding CLI optimized for it. Should also work on M1, M2, M3, M4 Macs.
Created this in 8 prompts. I need beta testers for the CLI. Pivoting to TypeScript for faster iteration. https://t.co/DHESMMbcp3
Similar Articles
@Daniel_Farinax: Qwen3.6-27B on MacBook Pro M5 128GB. Third version of the game. This time a low-poly GTA, built overnight using a custo…
Daniel Farinax demonstrates running Qwen3.6-27B on a MacBook Pro M5 128GB, using a custom Rust CLI (MPTLX) to build a low-poly GTA game overnight, claiming blazing fast performance comparable to Claude 4.6 running locally.
Qwen3.6-35B-A3B-Abliterated-Heretic-MLX-4bit
The user reviews a quantized and fine-tuned version of the Qwen3.6-35B model optimized for Apple Silicon via MLX, praising its speed, intelligence, and lack of safety disclaimers.
Running Qwen 3.6 35b MoE With Zoo Code On M1 Max is Amazing! Fully local, battery-powered coding powerhouse!
The article discusses running the Qwen 3.6 35b Mixture-of-Experts model locally on an Apple M1 Max Mac using Zoo Code, highlighting its capabilities as a battery-powered coding assistant.
Running Qwen3.5-122B on Mac Studio 96GB: Fixed 3 bugs that made long-context inference usable
Fixed three bugs in a qMLX fork for running Qwen3.5-122B on Mac Studio, reducing prefill time from minutes to sub-seconds for long-context inference; open-sourced the fork and benchmark script.
Qwen3.8-27B is now up to ~3× faster on Apple Silicon with mlx-dspark
mlx-dspark v0.10.0 adds support for Qwen3.8-27B on Apple Silicon, providing up to 3x faster inference through speculative decoding with lossless verification.