BoltzmannEntropy/metalQwen3
Metal GPU implementation of the Qwen3 transformer model on macOS with complete Apple Silicon compute shader acceleration.
This project provides a specialized implementation of the Qwen3 large language model, designed to run directly on macOS devices with Apple Silicon chips. It takes pre-trained Qwen3 models and processes them entirely on your Mac's GPU, delivering text generation outputs efficiently. This tool is for developers who build applications or services that need to integrate local, high-performance AI text generation capabilities directly on Apple Silicon Macs.
No commits in the last 6 months.
Use this if you are a macOS developer creating applications that require running Qwen3 large language models with optimal performance directly on Apple Silicon GPUs, without relying on cloud services or less optimized CPU fallbacks.
Not ideal if you are looking for a general-purpose AI development framework, need to deploy on non-Apple hardware, or require support for a wide range of different large language models beyond Qwen3.
Stars
43
Forks
5
Language
C++
License
MIT
Category
Last pushed
Oct 06, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/BoltzmannEntropy/metalQwen3"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
QwenLM/Qwen
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
LLM-Red-Team/qwen-free-api
🚀...
QwenLM/Qwen-VL
The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by...
willbnu/Qwen-3.5-16G-Vram-Local
Configs, launchers, benchmarks, and tooling for running Qwen3.5 GGUF models locally with...
QwenLM/qwen.cpp
C++ implementation of Qwen-LM