Instructions to use MusicForge/magnet-medium-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use MusicForge/magnet-medium-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download MusicForge/magnet-medium-4bit --local-dir magnet-medium-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
|
Download README.md from MusicForge/magnet-medium-4bit: direct link, hf CLI and curl.
- Browser
- Download file 1.94 kB
-
https://huggingface.co/MusicForge/magnet-medium-4bit/resolve/main/README.md
- Command line
-
hf download hf://MusicForge/magnet-medium-4bit/README.md
-
curl -L -o README.md https://huggingface.co/MusicForge/magnet-medium-4bit/resolve/main/README.md
1.94 kB
| license: cc-by-nc-4.0 | |
| language: | |
| - en | |
| tags: | |
| - mlx | |
| - audio | |
| - music | |
| - text-to-music | |
| - magnet | |
| - quantized | |
| - int4 | |
| base_model: facebook/magnet-medium-30secs | |
| library_name: mlx | |
| pipeline_tag: text-to-audio | |
| # MAGNeT-Medium-30secs-MLX-4bit | |
| - [speech-swift](https://github.com/soniqo/speech-swift) — Apple SDK | |
| - [soniqo.audio](https://soniqo.audio) — website | |
| - [blog](https://soniqo.audio/blog) — blog | |
| MLX port of Meta's [MAGNeT](https://arxiv.org/abs/2401.04577) — a masked | |
| parallel text-to-music model — quantized to **INT4** weight-only for | |
| on-device generation on Apple Silicon. EnCodec 32 kHz audio decoder; T5-base | |
| text encoder; per-codebook iterative decoding with restricted-context | |
| self-attention. | |
| ## Model | |
| | | | | |
| |---|---| | |
| | Parameters (LM) | 1.5B | | |
| | Quantization | INT4 weight-only, group size 64 | | |
| | Format | MLX safetensors | | |
| | Sample rate | 32 kHz mono | | |
| | Output length | 30 s per generation (fixed) | | |
| | Decoding steps | 50 total (`[20, 10, 10, 10]` across 4 RVQ codebooks) | | |
| | Bundle size | 1357 MB on disk | | |
| | Source | [facebook/magnet-medium-30secs](https://huggingface.co/facebook/magnet-medium-30secs) | | |
| ## Performance (Apple Silicon, 30 s audio) | |
| | Metric | Value | | |
| |---|---| | |
| | Real-time factor (wall / audio) | **1.20** | | |
| | Peak RSS | 2215 MB | | |
| | CLAP score (laion/clap-htsat-unfused, 5 prompts) | 0.334 | | |
| ## Usage | |
| ```python | |
| from huggingface_hub import snapshot_download | |
| bundle = snapshot_download("aufklarer/MAGNeT-Medium-30secs-MLX-4bit") | |
| # See https://github.com/soniqo/speech-swift for production usage. | |
| ``` | |
| ## Source | |
| - Upstream: [facebook/magnet-medium-30secs](https://huggingface.co/facebook/magnet-medium-30secs) | |
| - Paper: [MAGNeT (arxiv 2401.04577)](https://arxiv.org/abs/2401.04577) | |
| - Audiocraft: [facebookresearch/audiocraft](https://github.com/facebookresearch/audiocraft) | |
| ## License | |
| **CC-BY-NC 4.0** — inherited from upstream MAGNeT weights. Non-commercial use only. | |