Overview
StepFun’s multimodal reasoning foundation model, co-designed around MoE and MFA/AFD system components with 321B total and 38B active parameters.
StepFun’s multimodal reasoning foundation model, co-designed around MoE and MFA/AFD system components with 321B total and 38B active parameters.
Only published specifications are shown.
StepFun’s multimodal reasoning foundation model, co-designed around MoE and MFA/AFD system components with 321B total and 38B active parameters.
Step 3 is a key point where StepFun’s public-weight path moved from early product models to efficient multimodal reasoning and model-system co-design.
Step 3 multimodal reasoning foundation model was open-sourced.
View sourceSelect a card to view the related model.
Copy this template, add the field, proposed value, and primary source, and share it with the archive maintainer.