jjang-ai/jangq
JANG — GGUF for MLX. YOU MUST USE JANG_Q RUNTIME. Adaptive Mixed-Precision Quantization + Runtime for Apple Silicon
This helps Mac users run very large AI models, like large language models (LLMs) and vision-language models (VLMs), directly on their Apple Silicon Macs. It takes an existing model and optimizes it so it uses much less memory, allowing models that typically wouldn't fit to run faster and with better accuracy. This tool is for researchers, developers, or anyone who wants to run powerful AI models locally on their Mac without needing expensive cloud resources.
Use this if you need to run large AI models on your Apple Silicon Mac that would otherwise be too big or slow, especially if you're working with complex models like Mixture-of-Experts (MoE) architectures.
Not ideal if you are using non-Apple hardware, as this technology is specifically designed for Apple Silicon, or if you only work with small models that already run efficiently.
Stars
58
Forks
4
Language
Python
License
—
Category
Last pushed
Mar 26, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/jjang-ai/jangq"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ggml-org/ggml
Tensor library for machine learning
onnx/ir-py
Efficient in-memory representation for ONNX, in Python
R-D-BioTech-Alaska/Qelm
Qelm - Quantum Enhanced Language Model
SandAI-org/MagiCompiler
A plug-and-play compiler that delivers free-lunch optimizations for both inference and training.
bytedance/lightseq
LightSeq: A High Performance Library for Sequence Processing and Generation