Model reference · open weights

MiniMax-Music3-Serve

MiniMax-Music3-Serve is an open-weight audio or speech model from ddalcu, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Licence fee required Audio ddalcu 1 variants 1k downloads/mo
Request a licence + hosting quote All served models Not on the shared API today — deployed on request.

About

What MiniMax-Music3-Serve is

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, lmhead). 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). 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: Lyrics are required (the model is lyric-conditioned) and structure tags like [verse] or [chorus] go on their own lines. durationseconds (1-360) is an upper bound, the model may end the song earlier. ACE-Step style fields (bpm, keyscale, timesignature, vocallanguage) do not exist on this model. Rebuild from the upstream repo with scripts/convertmusic3weights.py. Weights are covered by the MiniMax-Music3 Community License (see LICENSE, acceptable-use policy included as Exhibit A).

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makerddalcu
TypeAudio & music
Variants1
Runs withmlx-serve
Based onMiniMaxAI/MiniMax-Music3
Released2026-08-13
Popularity1k downloads / month
Likes5
LicenceCommercial licence needed

How it works

How audio & music work

Audio or textinputAudio modelrecognise / synthesiseText or audiooutputSpeech-to-text turns audio into text; text-to-speech and music models turn text into audio.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
MiniMax-Music3-MLX-Serve-8bitMLXWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys minimax-music3-serve for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (minimax-music3-serve below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -F model="minimax-music3-serve" -F file=@audio.mp3

Details

Languages, data & research

Tags

mlx-serve safetensors minimax_music3 mlx music text-to-music minimax text-to-audio

Licence

Commercial licence needed

The weights are open but its licence needs a commercial agreement for business use. AxForge can arrange that licence and host the model for you — you pay AxForge, we settle with the model’s maker. Ask us for a quote. Read the licence ↗

Sources

Weights & code

Want MiniMax-Music3-Serve on EU-owned hardware?

Request a licence + hosting quote See what’s served now

Explore

More audio & music

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms