MiniMax Music 3 GGUF

GGUF package for MiniMax Music 3 for audio.cpp.

Upstream model: https://huggingface.co/MiniMaxAI/MiniMax-Music3 Upstream license: https://huggingface.co/MiniMaxAI/MiniMax-Music3/blob/main/LICENSE

The audio.cpp implementation is being staged on the preview/minimax-music-3 branch while the runtime surface is iterated quickly.

Preview Notes

  • The current runtime uses model-local resource loading instead of treating the v1 spec as the runtime contract. This keeps component selection flexible while the package layout and option surface settle.
  • The best quality/performance component combination is still being measured. The default favors Q4_K for the large language model and flow transformer, with BF16 kept for the RVQ depth decoder.
  • Longer generations such as five-minute songs are supported as long-form runs, but they are currently tuned for completion and quality checks rather than realtime throughput.
  • Memory usage is an active optimization target for larger durations and alternate component mixes.

Quick Start

audiocpp_cli \
  --task gen \
  --family minimax_music3 \
  --model MiniMax-Music3-GGUF \
  --backend cuda \
  --text "A bright pop rock song with clean drums and a clear male vocal." \
  --request-option 'lyrics=[verse] City lights are shining low. I keep moving with the glow. [chorus] Turn it up and let it fly. Sing the melody tonight.' \
  --request-option duration_sec=20 \
  --request-option num_inference_steps=30 \
  --out output.wav

Components

Default audio.cpp component mix:

  • language_model_q4_k.gguf
  • rvq_depth_decoder_bf16.gguf
  • transformer_q4_k.gguf
  • condition_encoder.gguf
  • vocoder.gguf

The BF16 and Q4_K component variants are included for measurement and quality/performance comparison.

Component GGUFs can be selected explicitly for experiments:

--session-option minimax_music3.language_model_gguf=language_model_bf16.gguf
--session-option minimax_music3.rvq_depth_decoder_gguf=rvq_depth_decoder_q4_k.gguf
--session-option minimax_music3.flow_transformer_gguf=transformer_bf16.gguf

License

This GGUF package follows the upstream MiniMax-Music3 COMMUNITY LICENSE. The license text is included in LICENSE; review it before use, especially for commercial deployment.

Downloads last month
-
GGUF
Model size
25.2M params
Architecture
audiocpp
Hardware compatibility
Log In to add your hardware

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for audio-cpp/MiniMax-Music3-GGUF

Quantized
(10)
this model