---
language:
- zh
- en
tags:
- speech
- text-to-speech
- speech-editing
- mlx
- apple-silicon
- audio
- 8bit
- quantized
license: mit
pipeline_tag: text-to-speech
---

# 🚀 AuK-Base-MLX-8bit (Apple Silicon 8-Bit Quantized)

<p align="center">
  <a href="https://github.com/vanch007/mlx-AuK"><b>🔗 GitHub Source & Web Demo: vanch007/mlx-AuK</b></a> ·
  <a href="https://huggingface.co/vanch007/AuK-Base-MLX"><b>Full Precision MLX Weights</b></a>
</p>

This repository provides the **8-Bit affine quantized MLX port** of **AuK Base**, Tencent Hunyuan's 1.5B speech foundation model.

- **Main GitHub Repository**: [https://github.com/vanch007/mlx-AuK](https://github.com/vanch007/mlx-AuK)
- **Original Project**: [Tencent-Hunyuan/AuK](https://github.com/Tencent-Hunyuan/AuK)
- **Quantization**: 8-bit group-wise affine quantization ()
- **Weight Size**: **0.56 GB** (90.1% reduction from 5.70 GB)