You can deploy this model and start earning money today!

mlx-community/
MiniMax-Music3-6bit

Name: MiniMax-Music3-6bit
Rating: 2.5 (134 reviews)

MiniMaxAI/MiniMax-Music3

quantized

other

6-bit

Views

No views yet

MiniMax Music 3 · MLX 6-bit

Native MLX affine 6-bit weights for MiniMaxAI/MiniMax-Music3, converted for lyric-conditioned song generation on Apple Silicon with mlx-audio.

Community conversion, not an official MiniMax release. All model credit goes to MiniMax. Review the original model card and license before use.

Other MLX variants: BF16 · 8-bit · 4-bit · MXFP8 · MXFP4 (experimental) · NVFP4 (experimental)

Install

MiniMax Music 3 support was merged upstream in Blaizzy/mlx-audio#888. Until a PyPI release includes it, install the upstream merge commit directly:

python -m pip install "mlx-audio @ git+https://github.com/Blaizzy/mlx-audio.git@784b29e2691a93ca7483147d86f61859dfaa6296"

Generate

bash

python -m mlx_audio.music.generate \
  --model mlx-community/MiniMax-Music3-6bit \
  --caption "Warm acoustic pop, 96 BPM, intimate female vocal" \
  --lyrics $'[verse]\nMorning light across the room\n[chorus]\nSing with me' \
  --duration 30 \
  --steps 30 \
  --seed 7 \
  --output song.wav

python

from mlx_audio.music import load

model = load("mlx-community/MiniMax-Music3-6bit")
result = next(
    model.generate(
        text="Warm acoustic pop, 96 BPM, intimate female vocal",
        lyrics="[verse]\nMorning light across the room\n[chorus]\nSing with me",
        duration=30,
        steps=30,
        seed=7,
    )
)
print(result.audio.shape, result.sample_rate)  # stereo, 44100 Hz

Lyrics are required by the checkpoint contract. Use [instrumental] explicitly for instrumental generation. Duration is a requested upper bound: the autoregressive stage may emit its end token early. Style, tempo, instrument, and vocal controls are probabilistic rather than strict.

Quantization and verification

Affine 6-bit weight quantization with group size 64.
Large linears in the global language model, RVQ depth decoder, and flow transformer are quantized. Embeddings, output heads, convolutions, condition encoder, and vocoder remain dense for fidelity.
The three weight shards total 11,683,414,161 bytes.
Strict loading and real generation produced finite 44.1 kHz stereo audio.
The mlx-audio regression suite passed 1,742 tests with 34 expected skips; the focused music, converter, and registry suite passed 43 tests and 3 subtests.

Converted with mlx-audio 0.4.8 development commit c2fa486 and MLX 0.31.2.

License

The weights remain subject to the MiniMax-Music3 Community License, including its acceptable-use and commercial terms. The full license text is included in this repository.