Step-Audio-2-mini
Official · BF16 · safetensors
Runtime certified: Transformers
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| BF16 | safetensors | 16 | Official | Runtime certified |
StepFun · Audio · Step-Audio 2
Step-Audio 2 mini: Specs, GPU requirements, hosting & deployment
Step-Audio 2 mini is a recent Audio release in the StepFun family, certified from its immutable official source revision.
Total parameters8.0B
Active parametersDense model
Context window32,768 tokens
Release statusRecent · Recent
ArchitectureDense Transformer
ModalitiesAudio, Text
LicenseApache License 2.0
Deployment stateDeployable with certified configuration
Commercial stateCommercial Use Allowed
Release date2025-08-28
Architecture, strengths and use cases
Step-Audio 2 mini is an official self-hostable StepFun release in the StepFun Audio track. It uses Dense Transformer, carries 8B, supports a verified context window of 32,768 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.
Step-Audio 2 mini uses Dense Transformer with 8B. The stored architecture profile records 64 layers, hidden width 8192, 64 attention heads and a 32,768 token context ceiling where the official configuration publishes those fields.
Verified Dense Transformer architecture
32,768 token certified context
Official BF16 checkpoint coverage
Private LLM inference
Agentic workflows
Long-context document processing
Audio understanding
Certified checkpoints and quantizations
Only exact, source-certified variants attached to this release are shown.
Recommended hardware
Use only the listed transformers 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.
Estimated weight memory15.35 GB
KV cache2 GB
Runtime overhead7.84 GB
Total with safety margin31.24 GB
Recommended best value
1× NVIDIA H200 SXM 141GB
141 GB total VRAM · nvswitch
109.76 GB headroom · Limited capacity
USD 2,345 / monthLowest-cost viable
2× NVIDIA L4 24GB
48 GB total VRAM · pcie
16.76 GB headroom · Available
USD 500 / monthHighest performance
1× NVIDIA H200 SXM 141GB
141 GB total VRAM · nvswitch
109.76 GB headroom · Limited capacity
USD 2,345 / monthLicense and self-hosting considerations
The full 8B 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.
Step-Audio 2 mini is published under Apache License 2.0. The release-scoped official license link and verification date are retained with the catalogue record.
Commercial Use Allowed. The official license permits commercial use; its obligations still apply.
Alternatives and sibling variants
Step-Audio R1.1, Step-Audio-2-mini
Release timeline
stepfun/stepfun/step-audio-2-mini
Source details
Source revision: 78fc4999e3d019c52880daa8c85099216f3e3ef53583974d3642f2c76bf2b106
Frequently asked questions
How much VRAM does Step-Audio 2 mini 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 Step-Audio 2 mini?
Certified upstream runtime evidence is available for transformers.
Can Step-Audio 2 mini be used commercially?
The stored commercial classification is Commercial Use Allowed. Consult the official Apache License 2.0 terms for the final obligations.
Official references
Last verified: 2026-08-26