stable-audio-3-small-music SAME-S needs about 0.6 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 11 quants, from 0.0 GB (F32) to 1.8 GB (F32).
Stable Audio 3 Small-Music GGUF model for music generation
Stable Audio 3 Small-Music is a lightweight music generator using the SAME-S autoencoder and a 0.5B DiT. It is available in multiple GGUF quantizations for sa3.cpp, supporting CPU, CUDA, Vulkan, and Metal. The model matches the PyTorch reference with cosine similarity ~1.0.
Good at
- Music generation
- Fast inference on GPUs
- Portable C++/GGML usage
Limits
- No vision support
- Requires even frame count for SAME-S
- License limited to organizations <$1M revenue
Best for
- Generating short music clips
- Embedding music into applications
- Testing music generation pipelines
Who it’s for. Developers and researchers needing a compact music generation model that runs on a variety of hardware, including laptops and Apple Silicon. The model is suitable for integration into media tools and rapid prototyping.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F32 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q5_K_M | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q8_0 | 0.1 GB | 0.6 GB | Fits | Get file → | |
| F16 | 0.2 GB | 0.7 GB | Fits | Get file → | |
| Q4_K_M | 0.3 GB | 0.9 GB | Fits | Get file → | |
| Q5_K_M | 0.4 GB | 0.9 GB | Fits | Get file → | |
| F32 | 0.4 GB | 1.0 GB | Fits | Get file → | |
| Q8_0 | 0.5 GB | 1.1 GB | Fits | Get file → | |
| F16 | 0.9 GB | 1.5 GB | Fits | Get file → | |
| F32 | 1.8 GB | 2.6 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (0.08 GB, 0.6 GB memory) or Q5_K_M (0.08 GB, 0.6 GB memory). If 4 GB VRAM is available, choose Q4_K_M (0.08 GB). For larger memory budgets, F16 (0.22 GB, 0.7 GB) or Q8_0 (0.12 GB, 0.6 GB) provide higher precision.
What GPU do you need for stable-audio-3-small-music SAME-S?
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: the best quant that fits is F32 (1.8 GB file, about 2.6 GB in use).
Which stable-audio-3-small-music SAME-S quant should you choose?
Q4_K_M is the usual starting point for stable-audio-3-small-music SAME-S: it balances file size and quality well. Here it is a 0.1 GB file.
The Q8_0 file is 0.1 GB, about 1.5 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is F32 at 0.0 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about stable-audio-3-small-music SAME-S
How much VRAM does stable-audio-3-small-music SAME-S need?
About 0.6 GB at Q4_K_M with an 8K context window. That is the 0.1 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 stable-audio-3-small-music SAME-S on an 8 GB GPU?
Yes, with F32: the 1.8 GB file needs about 2.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of stable-audio-3-small-music SAME-S GGUF?
It depends on the quant: F32 is 0.0 GB, Q4_K_M is 0.1 GB, Q5_K_M is 0.1 GB, Q8_0 is 0.1 GB, F16 is 0.2 GB, Q4_K_M is 0.3 GB and 5 more.
Where can I download stable-audio-3-small-music SAME-S GGUF?
The files are on Hugging Face in the thepatch/stable-audio-3-small-music-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 stable-audio-3-small-music SAME-S use?
Hugging Face lists the license as other. 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 Stable Audio 3 Small-Music on 8 GB VRAM?
Yes, the Q4_K_M or Q5_K_M quantizations use about 0.6 GB memory at 8k context, fitting within 8 GB VRAM.
Does the model support CUDA?
Yes, CUDA is supported and gains roughly 33% end‑to‑end speed on compatible GPUs.
What is the license for this model?
The model is released under the Stability AI Community License, free for organizations under $1M annual revenue with commercial use.