QwQ-32BOpen Weight
Released
QwQ-32B is an AI model released by Qwen on Thursday, Mar 6 2025, 37 days after Qwen2.5-Max. It is an open-weight model — the trained weights are available to download and run. It is a 32B parameterThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. model with a 128k token context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider.. Benchmark results (shown below) cover LiveCodeBench.
Get Qwen releases and AI news.
Every other Monday
Benchmarks
Compare QwQ-32B with
About
QwQ-32B was released on March 6, 2025 as a downloadable 32-billion-parameter reasoning model under Apache 2.0. It followed the experimental QwQ-32B-Preview and used reinforcement learning to improve work on mathematics, programming and other reasoning tasks.
The model supported a 128K context window and included training for agent behavior, using tool and environment feedback during multi-step work. Its dense architecture differed from larger mixture-of-experts systems in Qwen's comparisons. Deployment requirements still depended on numerical precision and serving settings, rather than parameter count alone.
Frequently asked questions
QwQ-32B was released by Qwen on Thursday, Mar 6 2025.