StepFun launches Step 5 preview: 600B sparse MoE, 1M context
StepFun Launches Step 5 Preview: 600B Sparse MoE, 1M Context, Weights Open Oct 15
This is the first 600B-scale model from a Chinese company to be released with open weights, offering a significant alternative to other large models.
StepFun has released the Step 5 preview, featuring a 600B/27B sparse MoE model with a 1M context length for long-term agents. The model's weights are set to be open on October 15.
StepFun Launches Step 5 Preview: 600B Sparse MoE, 1M Context, Weights Open Oct 15
StepFun’s Step 5 Preview pairs a 600B/27B sparse MoE with a 92-layer narrow-deep stack and 1M context for long-horizon agents, with weights planned for October 15.