Audio.cpp now supports MiniMax-Music3. No Python. Demo and performance metrics inside.
#24
by audio-cpp - opened
Check our repo https://github.com/0xShug0/audio.cpp. GGUFs here https://huggingface.co/audio-cpp/MiniMax-Music3-GGUF.
Measured on an RTX 5090 with CUDA using a 30-second lyric generation request (official prompt features/pop), 30 flow steps, flow guidance scale 1.7, AR guidance scale 1.5, and top-k 50. Peak VRAM is the observed nvidia-smi process peak during a warmup-plus-measured-request run.
| Component mix | Language model | RVQ depth decoder | Flow transformer | RTF | Speed | Peak VRAM |
|---|---|---|---|---|---|---|
| Default Q4/Q8/Q4 | q4_0 | q8_0 | q4_0 | 0.738 | 1.35× realtime | 9.8 GiB |
| Q8 | q8_0 | q8_0 | q8_0 | 0.832 | 1.20× realtime | 13.4 GiB |
| BF16 | bf16 | bf16 | bf16 | 1.389 | 0.72× realtime | 19.4 GiB |
Lower values such as 10 or 20 can be much faster, while still producing reasonable results depending on the prompt and seed.
Q8:
steps=10 rtf=0.597129
steps=20 rtf=0.719549
steps=30 rtf=0.824861
End to end demo:
audio-cpp changed discussion title from Audio.cpp now support MiniMax-Music3. No Python. Demo and performance metrics inside. to Audio.cpp now supports MiniMax-Music3. No Python. Demo and performance metrics inside.