stable-audio-open-small
stabilityai/stable-audio-open-small
Official · BF16 · safetensors
Runtime certified: Stable-audio-tools
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| BF16 | safetensors | 16 | Official | Runtime certified |
Stable Audio · General · Stable Audio Open Small
Stable Audio Open Small: Specs, GPU Requirements and License
Stable Audio Open Small is a current Audio Generation release in the Stable Audio family, certified from its immutable official source revision.
Unknown / Not Recommendable
Compare this model
Total parameters497M
Active parametersDense model
Context windowN/A / Not directly comparable
Release statusCurrent · Current
ArchitectureLatent audio diffusion transformer
ModalitiesText
LicenseNot officially published
Deployment stateDeployable with certified configuration
Commercial stateUnknown / Not Recommendable
Release date2025-05-12
Architecture, strengths and use cases
Stable Audio Open Small is an official self-hostable Stability AI release in the Stable Audio Audio Generation track. It uses Latent audio diffusion transformer, carries 0.497B, supports a verified context window of 0 tokens, and exposes only source-certified checkpoints and runtime combinations. Its release, license and deployment facts are tied to the official repository revision rather than inferred from the family name.
Stable Audio Open Small uses Latent audio diffusion transformer with 0.497B. The stored architecture profile records layers, hidden width , attention heads and a 0 token context ceiling where the official configuration publishes those fields.
Verified Latent audio diffusion transformer architecture
Official checkpoint and pipeline evidence
Official BF16 checkpoint coverage
Private LLM inference
Agentic workflows
Long-context document processing
Certified checkpoints and quantizations
Only exact, source-certified variants attached to this release are shown.
Recommended hardware
Use only the listed stable-audio-tools runtime configuration with the exact checkpoint precision. The recommendation engine checks weight memory, KV cache, runtime overhead, safety headroom, GPU architecture and topology before ranking rentable and reference hardware.
Unknown / Not Recommendable
Commercial rights are not verified, so this release is not commercially recommendable.
License and self-hosting considerations
The full 0.497B resident weight set must fit across the selected GPUs. Context and concurrency add KV-cache memory; MoE active parameters do not replace resident-weight memory.
Stable Audio Open Small is published under Not officially published. The release-scoped official license link and verification date are retained with the catalogue record.
Unknown / Not Recommendable. Commercial rights are not verified, so this release is not commercially recommendable.
Alternatives and sibling variants
Stable Audio Open 1.0
Release timeline
stability-ai/stable-audio/stable-audio-open-small
Source details
Source revision: d56806706dad6a4a66dfb9fe64d24d9054c9dc2f1775cd05fe47215f352ce9e3
Frequently asked questions
How much VRAM does Stable Audio Open Small require?
The exact estimate depends on checkpoint precision, context and concurrency; the page recommendation uses the certified memory engine and compatible runtime configurations.
Which runtimes support Stable Audio Open Small?
Certified upstream runtime evidence is available for stable-audio-tools.
Can Stable Audio Open Small be used commercially?
The stored commercial classification is Unknown / Not Recommendable. Consult the official Not officially published terms for the final obligations.
Official references
Last verified: 2026-09-03