Stable Audio 3 Medium
- Open weights
Prices
0 offerings · prices as listedNo priced offering is listed for this model yet.
Run locally
Weights: stabilityai/stable-audio-3-medium- Parameters 2.3B
- Dense
- Native precision BF16
- Max context not stated
Memory isn’t estimated for this type: it depends on resolution, length and pipeline. Its weights:
| Precision | Weights |
|---|---|
| BF16 (native)maker’s file | 8.6 GB |
Estimates; facts from the maker’s Hugging Face repositories, as of 2026-11-06. How it’s estimated
Cited scores
From third-party leaderboards, not measured by usNo cited leaderboard covers music generation yet. We will cite one when its license allows.
Changes
All changes →- New music model
Sources
- stabilityai/stable-audio-3-medium model card (opens in a new tab) huggingface.co · checked Nov 2, 2026
- stabilityai/stable-audio-3-medium · Hugging Face (opens in a new tab) huggingface.co · checked Nov 5, 2026
- Stable Audio 3.0, the model family built with open-weight models<br/> — Stability AI (opens in a new tab) stability.ai · checked Nov 2, 2026
- stabilityai/stable-audio-3-medium model card (opens in a new tab) huggingface.co · checked Nov 3, 2026
- stabilityai/stable-audio-3-medium files (opens in a new tab) huggingface.co · checked Oct 30, 2026
Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data
Stability AI · United Kingdom · stability.ai
Related models
Snapshots, the same family and other models from this provider