What are the hardware requirements for Step Audio 2 Mini?

Step Audio 2 Mini requires approximately 16.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Step Audio 2 Mini and how large is it?

Step Audio 2 Mini is developed by stepfun-ai, a model with 8.3b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Step Audio 2 Mini?

Step Audio 2 Mini is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Step Audio 2 Mini by stepfun-ai — VRAM 16.6GB

Name: Step Audio 2 Mini
Author: stepfun-ai

Step Audio 2 Mini is an open-source language model by stepfun-ai. Features: 8.3b LLM, VRAM: 16.6GB, License: apache-2.0, LLM Explorer Score: 0.27.

Arxiv:2507.16632 Any-to-any Custom code En Onnx Region:us Safetensors Sharded Step audio 2 Tensorflow Zh

Model Card on HF 🤗: https://huggingface.co/stepfun-ai/Step-Audio-2-mini

Step Audio 2 Mini Parameters and Internals

LLM Name	Step Audio 2 Mini
Repository 🤗	https://huggingface.co/stepfun-ai/Step-Audio-2-mini
Model Size	8.3b
Required VRAM	16.6 GB
Updated	2026-08-05
Maintainer	stepfun-ai
Model Type	step_audio_2
Model Files	4.9 GB: 1-of-4 4.9 GB: 2-of-4 5.0 GB: 3-of-4 1.8 GB: 4-of-4
Supported Languages	en zh
Model Architecture	StepAudio2ForCausalLM
License	apache-2.0
Model Max Length	131072
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Step Audio 2 Mini capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation