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:
1mlx-serve --serve
2curl http://127.0.0.1:11234/v1/audio/music-generations \
3 -H 'Content-Type: application/json' -o song.wav -d '{
4 "model": "MiniMax-Music3-MLX-Serve-8bit",
5 "prompt": "upbeat synthwave with driving bass and dreamy pads",
6 "lyrics": "[verse]\nneon lights across the bay\n[chorus]\nwe run all night",
7 "duration_seconds": 60
8 }'
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).