NeelM0906/Mference
Swift + Metal MoE inference for Apple Silicon: Qwen 3.6 35B at 23.5–29.3 tok/s decode with 2.20× faster long-prompt prefill on a 24 GB M5; Gemma 4 26B in ~2 GB, DeepSeek-V4-Flash 284B, Inkling-Small 2
- Stars
- 121
- Forks
- 16
- Open issues
- 1
- Last push
- 1mo ago
Mference star history
-1 this week
About Mference
Mference is a free, open-source AI inference tool by NeelM0906, written mainly in Swift. Swift + Metal MoE inference for Apple Silicon: Qwen 3.6 35B at 23.5–29.3 tok/s decode with 2.20× faster long-prompt prefill on a 24 GB M5; Gemma 4 26B in ~2 GB, DeepSeek-V4-Flash 284B, Inkling-Small 2. It has 121 GitHub stars and 16 forks, and was last updated 1mo ago. GitHub doesn't detect a standard license, so check the repository before using it commercially. According to the project, it works on macOS.
- License
- Not detected
- Commercial use
- No license
- Language
- Swift
- Stars
- 121
- Last update
- 1mo ago
- Runs on Mac
- Yes (as stated by the project)
- GPU
- Not stated
- Paid API key
- Not required
- Self-hostable
- Not stated
Similar free tools
llm-action25k stars · 本项目旨在分享大模型相关技术原理以及实战经验(大模型工程化、大模型应用落地)
ai-infra-book7.0k stars · 《深入理解 AI Infra:量化分析与系统设计》(李博杰 著)开源书稿:从硬件约束和模型架构出发,量化推导 LLM 推理与训练系统设计。含全书正文、PDF、配套计算工具与实验
TensorRT-LLM15k stars · Optimizes inference for large language models on NVIDIA GPUs.
vllm95k stars · High-throughput inference engine for LLMs.
vllm-metal1.9k stars · Community maintained hardware plugin for vLLM on Apple Silicon
llama.cpp132k stars · LLM inference in C/C++
Mference FAQ
Can I use Mference commercially?
Unclear. No license was detected, which legally means all rights are reserved. Ask the author before using it commercially. This is a plain-English summary, not legal advice.
Is Mference free?
Yes. Mference is open source and free to use. GitHub doesn't detect a standard license, so check the repository before using it commercially.
Does Mference run on a Mac?
Yes. According to the project, Mference works on macOS.
Does Mference need a GPU?
The project doesn't state hardware needs. AI models generally run much faster with a GPU.
Is Mference still maintained?
It was last updated 1mo ago. Check recent issues on GitHub to judge how active it is.
What are alternatives to Mference?
Similar free, open-source tools include llm-action, ai-infra-book, TensorRT-LLM, vllm.
Maintain Mference?
Add this badge to your README to show it's featured on FreeAIRepo.
[](https://www.freeairepo.com/repo/NeelM0906/Mference)