---
license: mit
tags:
  - mlx
  - audio
  - source-separation
  - music
  - apple-silicon
base_model:
  - facebook/demucs
library_name: mlx
---

# MLX Demucs Weights

Converted weights for [mlx-demucs](https://github.com/lextoumbourou/mlx-demucs), an Apple Silicon port of Meta's [Demucs](https://github.com/facebookresearch/demucs) audio source separation models using the [MLX](https://github.com/ml-explore/mlx) framework.

All models achieve <0.04% relative error vs the original PyTorch weights.

## Models

| Model | Stems | Notes |
|-------|-------|-------|
| `htdemucs` | drums, bass, other, vocals | Hybrid Transformer Demucs |
| `htdemucs_ft_drums` | drums, bass, other, vocals | Fine-tuned for drums |
| `htdemucs_ft_bass` | drums, bass, other, vocals | Fine-tuned for bass |
| `htdemucs_ft_other` | drums, bass, other, vocals | Fine-tuned for other |
| `htdemucs_ft_vocals` | drums, bass, other, vocals | Fine-tuned for vocals |
| `hdemucs_mmi` | drums, bass, other, vocals | Hybrid Demucs, no transformer |
| `htdemucs_6s` | drums, bass, other, vocals, guitar, piano | Experimental 6-stem model |

## Usage

Install [mlx-demucs](https://github.com/lextoumbourou/mlx-demucs) — weights are downloaded automatically on first use:

```bash
pip install mlx-demucs
mlx-demucs song.wav
mlx-demucs song.wav -m htdemucs_6s
```

Or use the Python API:

```python
from mlx_demucs.utils.loader import load_model

model = load_model("htdemucs")       # 4-stem
model = load_model("htdemucs_ft")    # 4-stem ensemble (best quality)
model = load_model("htdemucs_6s")    # 6-stem (experimental)
```

## Performance

~38x realtime on Apple Silicon.

## License

Weights are derived from [facebook/demucs](https://github.com/facebookresearch/demucs) and released under the MIT License. Copyright (c) Meta Platforms, Inc. and affiliates.