Part of the SongGeneration MLX conversion set. Collection: https://huggingface.co/collections/mlx-community/songgeneration-v2-mlx-6a1bf9342dd0806419737229
SongGeneration-v2-medium
Apple MLX weights for the autoregressive audiolm token generator from Tencent SongGeneration v2-medium.
This default repository is the bf16 variant and is equivalent to mlx-community/SongGeneration-v2-medium-bf16. Use this repo when you want the recommended default checkpoint.
This is not a full-stack pure MLX audio pipeline yet: token generation runs with MLX, while FLAC decoding currently uses the official PyTorch Flow1dVAE / separate-tokenizer bridge in ailuntx/SongGeneration-MLX.
TL;DR
| Variant | v2-medium |
| Precision | bf16 (bfloat16) |
| Converted component | SongGeneration audiolm token generator |
| Runtime | ailuntx/SongGeneration-MLX |
| Official model | tencent/SongGeneration |
| Official code | tencent-ailab/songgeneration |
Quick Start
git clone https://github.com/ailuntx/SongGeneration-MLX.git
cd SongGeneration-MLX
python -m venv .venv
.venv/bin/pip install -e .
.venv/bin/pip install -U huggingface_hub hf_transfer
HF_HUB_ENABLE_HF_TRANSFER=1 .venv/bin/hf download mlx-community/SongGeneration-v2-medium --local-dir ./models/SongGeneration-v2-medium
.venv/bin/python -m songgeneration_mlx.cli \
--model ./models/SongGeneration-v2-medium \
--lyrics '[verse] hello from mlx [chorus] sing it again' \
--description 'Pop, female vocal, bright production, [Musicality-medium].' \
--duration 2 \
--top-k 50 \
--temperature 0.9 \
--output tokens_2s.npz
Decode Tokens
The MLX runtime writes discrete song tokens. To create FLAC audio, use the official decoder bridge in ailuntx/SongGeneration-MLX. The bridge needs the official SongGeneration runtime/ assets, but it does not need the original SongGeneration LM model.pt when --mlx-model is used.
python -m venv .venv-decoder
.venv-decoder/bin/pip install -U pip
.venv-decoder/bin/pip install \
-r third_party/SongGeneration/requirements.txt \
-r third_party/SongGeneration/requirements_nodeps.txt \
soundfile
HF_HUB_ENABLE_HF_TRANSFER=1 .venv/bin/hf download tencent/SongGeneration \
--include "runtime/*" \
--local-dir ./third_party/SongGeneration
PYTORCH_ENABLE_MPS_FALLBACK=1 SONGGEN_DEVICE=mps \
.venv-decoder/bin/python scripts/decode_tokens_official.py \
--mlx-model ./models/SongGeneration-v2-medium \
--tokens ./tokens_2s.npz \
--output ./output_2s.flac \
--device mps
Variants
| Variant | Disk | Notes |
|---|---|---|
SongGeneration-v2-medium-fp32 | 10G | high-precision medium baseline |
SongGeneration-v2-medium | 5.2G | default medium checkpoint, same weights as bf16 |
SongGeneration-v2-medium-bf16 | 5.2G | explicit medium bf16 quality baseline |
SongGeneration-v2-medium-8bit | 2.8G | smaller medium checkpoint |
SongGeneration-v2-medium-4bit | 1.5G | smallest medium checkpoint |
SongGeneration-v2-large-fp32 | 19G | high-precision large baseline |
SongGeneration-v2-large-bf16 | 9.5G | large bf16 quality baseline |
SongGeneration-v2-large-8bit | 5.0G | smaller large checkpoint |
SongGeneration-v2-large-4bit | 2.7G | smallest large checkpoint |
SongGeneration-v2-fast-* | pending | upstream fast weights were not publicly available when checked on 2026-05-31 |
Layout
SongGeneration-v2-medium/
|-- model-00001-of-000xx.safetensors
|-- model.safetensors.index.json
|-- config.json
|-- mlx_manifest.json
|-- config.official.yaml
|-- vocab.yaml
`-- qwen2_tokenizer/
Validation
Local Apple Silicon validation was run on the medium bf16 path:
| Test | Result |
|---|---|
| 12s MLX token generation | 550 pattern steps, about 1 minute wall time |
| 12s official decoder bridge | 73.27s wall time |
| 12s FLAC | 48kHz stereo, 12.000s, RMS about 0.163 |
The official recent-token repetition penalty is implemented in the MLX runtime. Without it, 12s generations collapse into repeated tokens and decode close to silence.
License
License follows the upstream SongGeneration release. Check the official model card and repository for the authoritative model license.
Citation
@misc{songgeneration-mlx,
title = {SongGeneration-MLX: Apple MLX port of SongGeneration},
author = {ailuntx},
year = {2026},
url = {https://github.com/ailuntx/SongGeneration-MLX},
}
@article{lei2025levo,
title = {LeVo: High-Quality Song Generation with Multi-Preference Alignment},
author = {Lei, Shun and Xu, Yaoxun and Lin, Zhiwei and Zhang, Huaicheng and Tan, Wei and Chen, Hangting and Yu, Jianwei and Zhang, Yixuan and Yang, Chenyu and Zhu, Haina and Wang, Shuai and Wu, Zhiyong and Yu, Dong},
journal = {arXiv preprint arXiv:2506.07520},
year = {2025},
}