metadata
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 — Apple SDK
- soniqo.audio — website
- blog — blog
MLX port of Meta's MAGNeT — 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 |
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
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
- Paper: MAGNeT (arxiv 2401.04577)
- Audiocraft: facebookresearch/audiocraft
License
CC-BY-NC 4.0 — inherited from upstream MAGNeT weights. Non-commercial use only.