Stability AI · First MLX build 11 Nov 2026
stable-audio-3-medium
MLX
Audio stable-audio-community New
A 1.9B parameter text to audio model from Stability AI, with one MLX build.
- Parameters
- 1.9B From Hugging Face
- Quantisation
- Unstated stable-audio-3-medium
- Memory needed
- 8 GB Estimate, unified memory
- Download
- 4.6 GB Weights, estimated
- Downloads
- 39 This build, last 30 days
- Task
- Text to audio Audio
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 8 GB at Unstated
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/stable-audio-3-mediumMLX builds
1 on mlx-community| stable-audio-3-medium | Unstated | 4.6 GB | 8 GB | 39 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.