Instructions to use ddalcu/MiniMax-Music3-MLX-Serve-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use ddalcu/MiniMax-Music3-MLX-Serve-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir MiniMax-Music3-MLX-Serve-8bit ddalcu/MiniMax-Music3-MLX-Serve-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
MiniMax Music 3 for mlx-serve (8-bit)
MiniMax-Music3 converted for mlx-serve's native Zig + MLX engine. Full songs with sung lyrics at 44.1 kHz stereo, generated locally on Apple Silicon.
Quantization: affine 8-bit, group 64, on every real matmul (LLM, depth decoder, DiT, lm_head). Kept dense on purpose: the embedding tables (gather reads), the condition encoder and the whole vocoder (VAE-class precision). Worst per-tensor reconstruction error 1.48% RMS. 13 GB on disk instead of the 57 GB upstream repo (which ships its weights twice).
| File | Contents |
|---|---|
language_model.safetensors |
Qwen3 8B global LLM, 36L, vocab 200k |
rvq_depth_decoder.safetensors |
0.6B local LLM, 7 residual codebooks |
transformer.safetensors |
2.4B flow-matching DiT, 36 blocks |
condition_encoder.safetensors |
hidden-state mix + resampler, f32 |
vocoder.safetensors |
Flow-VAE / DAC decoder, f32 |
Engine parity against the fp32 reference on these exact weights: prefill cosine 0.9999, condition encoder 0.999999, DiT velocity 0.999, vocoder 1.000000. The autoregressive stage runs about 44 ms per frame on an M-series Mac, so a one-minute song takes roughly a minute of LLM time plus the diffusion pass.
Run it
Download MLX Core.app, open the Music tab and pick MiniMax Music 3. Style prompt + lyrics in, WAV out.
Over HTTP:
mlx-serve --serve
curl http://127.0.0.1:11234/v1/audio/music-generations \
-H 'Content-Type: application/json' -o song.wav -d '{
"model": "MiniMax-Music3-MLX-Serve-8bit",
"prompt": "upbeat synthwave with driving bass and dreamy pads",
"lyrics": "[verse]\nneon lights across the bay\n[chorus]\nwe run all night",
"duration_seconds": 60
}'
Lyrics are required (the model is lyric-conditioned) and structure tags like
[verse] or [chorus] go on their own lines. duration_seconds (1-360) is
an upper bound, the model may end the song earlier. ACE-Step style fields
(bpm, keyscale, timesignature, vocal_language) do not exist on this model.
Rebuild from the upstream repo with
scripts/convert_music3_weights.py.
Weights are covered by the MiniMax-Music3 Community License (see LICENSE,
acceptable-use policy included as Exhibit A).
- Downloads last month
- -
Quantized
Model tree for ddalcu/MiniMax-Music3-MLX-Serve-8bit
Base model
MiniMaxAI/MiniMax-Music3