Qwen3MoE
This model was released on 2025-04-29 and added to Hugging Face Transformers on 2025-03-31.
Qwen3MoE
Section titled “Qwen3MoE”Overview
Section titled “Overview”Qwen3MoE refers to the mixture of experts model architecture Qwen3-235B-A22B which was released with its dense variant Qwen3 (blog post).
Model Details
Section titled “Model Details”To be released with the official model launch.
Usage tips
Section titled “Usage tips”To be released with the official model launch.
Qwen3MoeConfig
Section titled “Qwen3MoeConfig”[[autodoc]] Qwen3MoeConfig
Qwen3MoeModel
Section titled “Qwen3MoeModel”[[autodoc]] Qwen3MoeModel - forward
Qwen3MoeForCausalLM
Section titled “Qwen3MoeForCausalLM”[[autodoc]] Qwen3MoeForCausalLM - forward
Qwen3MoeForSequenceClassification
Section titled “Qwen3MoeForSequenceClassification”[[autodoc]] Qwen3MoeForSequenceClassification - forward
Qwen3MoeForTokenClassification
Section titled “Qwen3MoeForTokenClassification”[[autodoc]] Qwen3MoeForTokenClassification - forward
Qwen3MoeForQuestionAnswering
Section titled “Qwen3MoeForQuestionAnswering”[[autodoc]] Qwen3MoeForQuestionAnswering - forward