Qwen-72BOpen Weight
Released
Qwen-72B is an AI model released by Qwen on Thursday, Nov 30 2023, 119 days after Qwen-7B. It is an open-weight model — the trained weights are available to download and run. It is a 72B 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 32k 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..
Get Qwen releases and AI news.
Every other Monday
Compare Qwen-72B with
Suggested comparisons
Qwen-72BvsQwen3.8-Max-0902Qwen-72BvsGPT-6.1 TerraQwen-72BvsClaude Haiku 5.5Qwen-72BvsGemini 4 CarbonQwen-72BvsMuse Spark OpenQwen-72BvsGrok 4.7Qwen-72BvsDeepSeek-V4.1-Flash-1017Qwen-72BvsMistral Large 4Qwen-72BvsKimi K3.1 ProQwen-72BvsGLM-5.3-FlashQwen-72BvsNemotron 3.5 Bolt E4B 4GBAbout
Qwen-72B was released in November 2023 alongside Qwen-1.8B, expanding the original Qwen family. Alibaba supplied base and chat checkpoints for developers choosing a larger language model for self-hosted applications.
The model documentation described three trillion pretraining tokens and a 32,000-token context window. Its custom license differed from standard permissive software licenses. The original Qwen-72B also preceded Qwen1.5-72B and Qwen2-72B, which were separate releases despite sharing a parameter count.
Frequently asked questions
Qwen-72B was released by Qwen on Thursday, Nov 30 2023.