>>

Run Step-Audio-2-mini on Lium

StepFun · Multimodal · 8.3B parameters · 16.6 GB BF16 weights · released 2025-08-28
It needs about 20 GB of VRAM. The cheapest setup that runs it is RTX A4500 (20 GB), from $0.16 per hour, billed per second.
Rent RTX A4500

Other GPUs that run it

RTX 309024 GBfrom $0.19 / hourRent
L40S48 GBfrom $0.38 / hourRent

How to run it

Rent the pod above, open a terminal over SSH or Jupyter and serve stepfun-ai/Step-Audio-2-mini:
vllm serve stepfun-ai/Step-Audio-2-mini
Claude Code and Codex can do all of it through the Lium CLI.

Frequently asked questions

How much VRAM does Step-Audio-2-mini need?

About 16.6 GB for the released BF16 weights, so plan on 20 GB with room for activations and KV cache at a short context. Longer contexts and bigger batches need more.

What GPU should I rent to run Step-Audio-2-mini?

RTX A4500 (20 GB). On Lium that setup costs from $0.16 per hour, billed per second with no minimum.
All open models
For AI agents (CLI install, agent skill, headless signup): llms-full.txt