[audio.cpp] C++/GGML MiniMax-Music3. Fits comfortably within 16 GB VRAM and supports CUDA, Vulkan, Metal, and AMD GPUs. Demo included.

Open

#6 opened on Aug 21, 2026 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language: No language data
Stars: 896
Forks: 84
PR merge metrics: No merged PRs in 30d

Description

Repo: https://github.com/0xShug0/audio.cpp

Measured on an RTX 5090 with CUDA using a 30-second lyric generation request, 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	1.35x faster realtime	9.8 GiB
Q8	q8_0	q8_0	q8_0	0.832	1.20x faster realtime	13.4 GiB
BF16	bf16	bf16	bf16	1.389	0.72x realtime	19.4 GiB

60s and 180s (target duration) end to end demo, using the features/pop prompt from official demo

https://github.com/user-attachments/assets/4ecd1de8-fffd-4413-93e3-567eacc43843

Contributor guide

No contributing guide indexed for this repository

First steps

Read the whole issue, then the project's contributing guide.
Comment on the issue to say you are picking it up — it saves two people doing the same work.
Fork the repository and make your change on a branch.
Open a pull request that references the issue number.

Research direction

Start by reviewing the issue's audio.cpp/GGML implementation description and the linked 60s and 180s demo material. The issue does not name files, tests, an entry point, or a requested change, so a contributor would need clarification before work can be considered complete.

Written by the indexing model from the issue text.

Assessment

Tech stack: cpp
Domain: audio-video-rtc
Issue type: Feature
Difficulty: 5/5
Estimated time: Over a week
Activity status: Quiet
Clarity: Needs clarification
Newbie friendliness: 25/100

A short digest of beginner-friendly GitHub issues.