# StepFun opens weights for Step 5 preview model

> StepFun posted FP8 and BF16 checkpoints for its 600 billion‑parameter Mixture‑of‑Experts model, which runs 27 billion active parameters per token and supports up to 1 million token context.

Oossa · 2026-10-17 · https://oossa.com/en/stepfun-opens-weights-for-step-5-preview-model

StepFun has made its Step 5 preview model available as open weights. The checkpoints, in FP8 and BF16 formats, are posted on Hugging Face and ModelScope. The model is a sparse Mixture‑of‑Experts (MoE) system with 600 billion total parameters but only 27 billion active per token. It can handle contexts up to 1 million tokens, aimed at long‑horizon agentic tasks.

## The facts

- 600 billion total parameters, 27 billion active per token
- Context window up to 1 million tokens

## Why it matters

Developers can now experiment with a very large, open‑weight model that supports much longer text inputs than typical LLMs.

## Sources & references

1. [StepFun Releases Step 5 Preview Open Weights: 600B MoE, 27B Active, 1M Context](https://www.marktechpost.com/2026/10/16/stepfun-releases-step-5-preview-open-weights-600b-moe-27b-active-1m-context/) – MarkTechPost, 2026-10-17

Last updated: 2026-10-17