Skip to content
appsgit

MTPLX

MTPLX is a free, open-source AI desktop app for macOS. The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. It has 2,536 GitHub stars and is released under the Apache-2.0 license.

github.com/youssofal/MTPLX (opens in a new tab)

About MTPLX

MTPLX is a native Mac app and a command line that runs local language models on Apple Silicon with the model's own multi-token prediction (MTP) heads. It runs Qwen 3.8 Flash Next, the 125B mixture of experts, Qwen 3.8 27B and Prism ML's Ternary Bonsai 2 27B, plus Qwen 3.6, Qwen 3.5 and Gemma 4. The model drafts several tokens ahead of itself, one batched forward pass verifies the draft, and tokens are committed through exact rejection sampling with residual correction.

FAQ

MTPLX FAQ

Still curious? Email info@appsgit.com.

What is MTPLX?

MTPLX is a free, open-source AI desktop app for macOS. The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. It has 2,536 GitHub stars and is released under the Apache-2.0 license.

Is MTPLX free and open source?

Yes. MTPLX's source code is public on GitHub under the Apache-2.0 license, which is OSI-approved or FSF-free, so you can use, copy and change it for free.

How do I install MTPLX?

Download the installer for macOS from its GitHub Releases page (latest: v2.12.2) or the project website.

Is MTPLX still maintained?

The repository's most recent commit was on Oct 3, 2026. appsgit only lists apps whose repository had a commit in the last six months.