Qwen3-32B

NewReasoning LLM

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support. With this model, reasoning can be disabled by using \"/no_think\" in your prompts.

About Qwen3-32B model

Published on huggingface

05/03/2025


Input price

0.08 /Mtoken(input)

Output price

0.23 /Mtoken(output)


Supported Features
Function callingReasoningStreaming
Output Formats
raw_textjson_objectjson_schema
Context Sizes
32k
Parameters
32.8B

Try out the model by playing with it.