youssofal/MTPLX
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. Native MTP speculative decoding on Apple
- Stars
- 2.6k
- Forks
- 203
- Open issues
- 32
- Last push
- 12d ago
About MTPLX
MTPLX is a free, open-source LLM chat app by youssofal, written mainly in Python. 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. Native MTP speculative decoding on Apple. It has 2.6k GitHub stars and 203 forks, and was last updated 12d ago. It's released under the Apache-2.0 license, a standard open-source license. According to the project, it works on macOS.
- License
- Apache-2.0
- Language
- Python
- Stars
- 2,623
- Last update
- 12d ago
- Runs on Mac
- Yes (as stated by the project)
- GPU
- Not stated
- Paid API key
- Not stated
- Self-hostable
- Not stated
Similar free tools
rtk84k stars · CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
open-webui156k stars · User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
omlx23k stars · LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
llamafile26k stars · Distribute and run LLMs with a single file.
khoj38k stars · Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI
one-api37k stars · LLM API 管理 & 分发系统，支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 适配，可用于 key 管理与二次分发。单可执行文件，提供 Docker 镜像，一键部署，开箱即用。LLM API management & key
MTPLX FAQ
Is MTPLX free?
Yes. MTPLX is open source and free to use. It's released under the Apache-2.0 license, a standard open-source license.
Does MTPLX run on a Mac?
Yes. According to the project, MTPLX works on macOS.
Does MTPLX need a GPU?
The project doesn't state hardware needs. AI models generally run much faster with a GPU.
Is MTPLX still maintained?
Yes. It was last updated 12d ago and has 32 open issues on GitHub.
What are alternatives to MTPLX?
Similar free, open-source tools include rtk, open-webui, omlx, llamafile.