HeartMuLa-GGUF

HeartMuLa Q8_0 GGUF (happy-new-year) — for MindMuse

GGUF quantization of the HeartMuLa-oss-3B-happy-new-year open music foundation model, packaged as a single self-contained file for local, Apple-Silicon-native inference.

• Original model: HeartMuLa/HeartMuLa-oss-3B-happy-new-year
• Used by: MindMuse — a local music generation & speech studio for macOS
• File: heartmula-q8_0.gguf
• Quantization: Q8_0 (GGUF)
• License: Apache 2.0 (same as upstream)

What is this?

This is the [happy-new-year] themed fine-tune of the HeartMuLa 3B open music foundation model, converted to a single self-contained Q8_0 GGUF. It generates complete songs from style tags and structured lyrics, with controllable song structure and multilingual vocal conditioning (Chinese, English, Japanese, Korean, Spanish).

Usage

In MindMuse

No manual steps needed. MindMuse's built-in Model Manager downloads this GGUF automatically from this repo when you install HeartMuLa in Settings → Music Models.

Download MindMuse →

License

Apache 2.0. Please refer to the original model card and the HeartMuLa project for full terms and citations.

Links

• Original model: HeartMuLa-oss-3B-happy-new-year
• HeartMuLa GitHub: https://github.com/HeartMuLa/heartlib
• Paper: https://arxiv.org/abs/2601.10547
• Demo: https://heartmula.github.io/
• MindMuse: https://themindstudio.cc/mindmuse

Citation

If you find HeartMuLa useful, please cite:

@misc{yang2026heartmulafamilyopensourced,
      title={HeartMuLa: A Family of Open Sourced Music Foundation Models},
      author={Dongchao Yang and Yuxin Xie and Yuguo Yin and Zheyu Wang and Xiaoyu Yi and Gongxi Zhu and Xiaolong Weng and Zihan Xiong and Yingzhe Ma and Dading Cong and Jingliang Liu and Zihang Huang and Jinghan Ru and Rongjie Huang and Haoran Wan and Peixu Wang and Kuoxi Yu and Helin Wang and Liming Liang and Xianwei Zhuang and Yuanyuan Wang and Haohan Guo and Junjie Cao and Zeqian Ju and Songxiang Liu and Yuewen Cao and Heming Weng and Yuexian Zou},
      year={2026},
      eprint={2601.10547},
      archivePrefix={arXiv},
      primaryClass={cs.SD},
      url={https://arxiv.org/abs/2601.10547},
}