audio.cpp needs about 12.5 GB of memory at its main file (a 10.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 4 quants, from 10.7 GB to 15.3 GB (BF16).
ACE-Step 1.5 XL – 4B SFT audio model for high‑quality music generation
ACE-Step 1.5 XL is a 4B parameter supervised fine‑tuned model. It supports classifier‑free guidance for precise prompt control. The model is available in GGUF format and can be run with llama.cpp.
Good at
- High‑quality music generation
- CFG support for prompt adherence
- Commercial‑ready output
Limits
- Requires 12.5 GB VRAM for 8 k context (unknown quant)
- Large file size (~10.71 GB)
- No vision capabilities
Best for
- Creating royalty‑free music tracks
- Generating vocal samples with lyrics
- Producing background music for media
Who it’s for. Developers and content creators who need a reliable audio generation model that can be run locally. The model is licensed under MIT and is suitable for commercial use.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 10.7 GB | 12.5 GB | Too big | Get file → | |
| — | 10.7 GB | 12.5 GB | Too big | Get file → | |
| BF16 | 15.3 GB | 17.6 GB | Too big | Get file → | |
| BF16 | 15.3 GB | 17.6 GB | Too big | Get file → |
For 8 GB VRAM use the unknown quant file (~10.71 GB). If more VRAM is available, the BF16 quant (~15.28 GB) provides higher precision. Memory estimates are approximate and depend on context length.
What GPU do you need for audio.cpp?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is the main file (10.7 GB file, about 12.5 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (15.3 GB file, about 17.6 GB in use).
Which audio.cpp quant should you choose?
If memory is tight, the smallest file is the first one in the table at 10.7 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about audio.cpp
How much VRAM does audio.cpp need?
About 12.5 GB at its main file with an 8K context window. That is the 10.7 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run audio.cpp on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of audio.cpp GGUF?
It depends on the quant: file is 10.7 GB, file is 10.7 GB, BF16 is 15.3 GB, BF16 is 15.3 GB.
Where can I download audio.cpp GGUF?
The files are on Hugging Face in the CaptainArni/audio.cpp-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does audio.cpp use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run this model on 8 GB VRAM?
The unknown quant file requires about 12.5 GB VRAM at 8 k context, so 8 GB is insufficient.
Is the model suitable for commercial music production?
Yes, the model is trained on licensed and public domain data and is MIT‑licensed for commercial use.
Does the model support vision or image inputs?
No, the model only processes audio and text prompts.