Step-Audio-R1.1
Official · BF16 · safetensors
Runtime certified: Transformers
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| BF16 | safetensors | 16 | Official | Runtime certified |
StepFun · Audio · Step-Audio R1.1
Step-Audio R1.1: Specs, GPU requirements, hosting & deployment
Step-Audio R1.1 is a current Audio release in the StepFun family, certified from its immutable official source revision.
Total parameters33.5B
Active parametersDense model
Context window65,536 tokens
Release statusCurrent · Current
ArchitectureDense Transformer
ModalitiesText
Licenseapache-2.0
Deployment stateDeployable with certified configuration
Commercial stateCommercial Use Allowed
Release date2026-01-14
Architecture, strengths and use cases
Step-Audio R1.1 is an official self-hostable StepFun release in the StepFun Audio track. It uses Dense Transformer, carries 33.5B, supports a verified context window of 65,536 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 R1.1 uses Dense Transformer with 33.5B. The stored architecture profile records 64 layers, hidden width 8192, 64 attention heads and a 65,536 token context ceiling where the official configuration publishes those fields.
Verified Dense Transformer architecture
65,536 token certified context
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 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 memory64.27 GB
KV cache2 GB
Runtime overhead16.67 GB
Total with safety margin102.85 GB
Recommended best value
2× NVIDIA A100 SXM 80GB
160 GB total VRAM · nvlink
57.15 GB headroom · Available
USD 1,830 / monthLowest-cost viable
5× NVIDIA L4 24GB
120 GB total VRAM · pcie
17.15 GB headroom · Available
USD 1,250 / monthHighest performance
2× NVIDIA A100 SXM 80GB
160 GB total VRAM · nvlink
57.15 GB headroom · Available
USD 1,830 / monthLicense and self-hosting considerations
The full 33.5B 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 R1.1 is published under apache-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 2 mini, Step-Audio-2-mini
Release timeline
stepfun/stepfun/step-audio-r1-1
Source details
Source revision: 11a5ae11040a8f5b7cbc16a1bb4bf1be3b9871a0ea308b8e57a146ecd767ed1e
Frequently asked questions
How much VRAM does Step-Audio R1.1 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 R1.1?
Certified upstream runtime evidence is available for transformers.
Can Step-Audio R1.1 be used commercially?
The stored commercial classification is Commercial Use Allowed. Consult the official apache-2.0 terms for the final obligations.
Official references
Last verified: 2026-09-03