---
title: "StepFun releases Step 5 Preview, a 600B open-weight MoE model"
url: https://www.parallelquant.com/posts/stepfun-releases-step-5-preview-a-600b-open-weight-moe-model-6d2773
source_name: "MarkTechPost"
source_url: https://www.marktechpost.com/2026/10/16/stepfun-releases-step-5-preview-open-weights-600b-moe-27b-active-1m-context/
published: 2026-10-17T06:29:55.000Z
topics: ["llms", "open source"]
publisher: "Parallel Quant"
---

# StepFun releases Step 5 Preview, a 600B open-weight MoE model

*2026-10-17 · Source: [MarkTechPost](https://www.marktechpost.com/2026/10/16/stepfun-releases-step-5-preview-open-weights-600b-moe-27b-active-1m-context/)*

StepFun released Step 5 Preview as open weights, with FP8 and BF16 checkpoints on Hugging Face and ModelScope. It is a sparse Mixture-of-Experts model with 600B total and 27B active parameters per token, and supports up to 1M tokens of context. It is built for long-horizon agentic work.

**Why it matters:** Alongside Meta's Muse Spark Open, NVIDIA's Nemotron and DeepSeek, it adds to a wave of large open-weight models from Chinese and US labs, even as China weighs export controls on such models. The low active-parameter count makes a 1M-context agentic model cheaper to serve than its size suggests.

**Topics:** llms, open source

---
Read the original: https://www.marktechpost.com/2026/10/16/stepfun-releases-step-5-preview-open-weights-600b-moe-27b-active-1m-context/
Canonical: https://www.parallelquant.com/posts/stepfun-releases-step-5-preview-a-600b-open-weight-moe-model-6d2773
Published by Parallel Quant — https://www.parallelquant.com