StepFun makes Step Audio 2 Mini, an open-source multimodal chat model that takes in text, images, and audio and outputs text, images, and audio. It is built for audio understanding, speech conversation, and can call tools for web search and functions.
Input
Output
Context
16K
Max Output
-
Parameters
8.3B
Input Modalities
Output Modalities
None the catalog can show from stated facts or measured scores.
Download 16.6 GB
| Precision | Weights | One request at 16K tokens | Smallest GPU that fits |
|---|---|---|---|
| FP16 / BF16 | 15.5 GB | 18.1 GB | 1x NVIDIA GeForce RTX 3090 (24 GB) |
| INT8 | 7.74 GB | 9.92 GB | 1x NVIDIA T4 (16 GB) |
| INT4 | 3.87 GB | 5.86 GB | 1x NVIDIA T4 (16 GB) |
Computed by Inferbase from the 8,315,179,264 parameters in the creator's Hugging Face repository; one request adds its KV cache, activations and framework overhead, with the layer layout estimated from the parameter count.
Public resources
Specification sources
As of Nov 11, 2026.
Answered from the facts on this page, with their sources.
Step Audio 2 Mini has a context window of 16,384 tokens (source: Creator or provider API). A provider may serve less; Inferbase routes on what each provider serves.
Yes. Step Audio 2 Mini is an open-weight model under the Apache 2.0 license. You can download and self-host it within the license terms.
Step Audio 2 Mini has 8,315,179,264 parameters (8.3B), as stated in the creator's Hugging Face repository.
Strengths: Open weights under a permissive license (apache-2.0). Each is computed from the model's stated facts and benchmark results.
Step Audio 2 Mini accepts Text, Image and Audio and produces Text, Image and Audio. The Capabilities card lists the API features it supports, such as function calling and structured output.
No benchmark source has published a result for Step Audio 2 Mini yet, so it is shown as unmeasured, not estimated.
Not on Inferbase Managed today. Add your own provider key or endpoint that serves Step Audio 2 Mini, and Inferbase runs it on your account with the same routing and logs.
The weights take 15.5 GB at FP16 / BF16, 7.7 GB at INT8, 3.9 GB at INT4, computed from the 8,315,179,264 parameters its creator publishes. Each request adds its KV cache and the framework's overhead. The hardware section shows one request and the smallest GPU that fits; the GPU planner sizes it for your context length and traffic.
The model card of Step Audio 2 Mini lists 2 languages: English and Chinese. That is what StepFun states; the catalog does not test language quality.
Start on the free plan with 5,000 requests a month, no card required.