GGUF conversions of music and speech models for audio.cpp, the ggml-based native audio inference framework.

* proposed in audio.cpp#464; until that lands, download the file and point --model at its directory.

The XL DiT is the larger ACE-Step 1.5 transformer: 32 layers of 2560 against turbo's 24 of 2048, with 32 attention heads of 128. Each file is self-contained the way audio.cpp's other ACE-Step GGUFs are — XL DiT, planner LM, text encoder and VAE in one file — so none of them needs another download.

XL Turbo is guidance-distilled and ignores guidance_scale; XL SFT takes the CFG path. Both were converted from the float32 upstream snapshots.

ace_step is graded No (planner sampling can fail) for q8_0 in audio.cpp's gguf.md, and that grade is about the planner LM, not the DiT. The q8dit files quantise the DiT to q8_0 and keep the planner LM, text encoder and VAE at bf16:

Measured on an RTX 5090 (CUDA), against the bf16 file at the same prompt and seed:

Every build is deterministic at a fixed seed (run-to-run correlation 1.0000), so the last column isolates what quantisation changes. On a sung 40 s take the q8dit build scores 0.997 for XL Turbo and 0.999 for XL SFT, and an ASR pass over both returns the same lyric line. A fully quantised build returns a different song from the same seed — it plays, it just isn't the same model.

Validated on three prompts on one machine. Treat these as a preview: they are not covered by audio.cpp's path-test matrix.

The q8dit ids arrive with audio.cpp#464; until then, download the file and point --model at its directory.

The DiT variant is a load option, so name it explicitly:

For sung vocals, pass the lyrics and a language, and give the DiT more steps than the turbo default:

XL support landed in audio.cpp via PR #235; see docs/models/ace_step.md there for the full option reference and for rebuilding these files yourself.

Weights are MIT-licensed by ACE-Step; this repository only redistributes them in a different container format.