StepFun Releases Step 5 Preview Open Weights: 600B MoE, 27B Active, 1M Context
Quick Answer
StepFun has unveiled Step 5 Preview with open weights, featuring a 600B parameter sparse Mixture-of-Experts model.
Quick Take
It supports 27B active parameters per token and offers a context length of up to 1M tokens, available in FP8 and BF16 formats on Hugging Face and ModelScope.
Key Points
- Step 5 Preview features a total of 600 billion parameters.
- The model allows for 27 billion active parameters per token.
- It can handle context lengths of up to 1 million tokens.
- Available checkpoints are in FP8 and BF16 formats.
- The model is designed for long-horizon agentic tasks.
Article Excerpt
From source RSS / original summaryStepFun has released Step 5 Preview as open weights. FP8 and BF16 checkpoints are live on Hugging Face and ModelScope. Step 5 Preview is a sparse Mixture-of-Experts model from StepFun built for long-horizon agentic work. It has 600B total parameters, 27B active per token and up to 1M tokens of context. For developers, this is […] The post StepFun Releases Step 5 Preview Open Weights: 600B MoE, 27B Active, 1M Context appeared first on MarkTechPost.
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from MarkTechPost
See more →Microsoft AI Releases Microsoft-Decision-1: A Qwen3.5-9B Decision-Scoring Model
Microsoft has launched Microsoft-Decision-1, a decision-scoring model derived from Alibaba's Qwen3.5-9B. This model focuses on routing, classification, verification, and agent control, providing calibrated probabilities for fixed answer options instead of generating text. It is now available in Microsoft Foundry and OpenRouter.