Qwen1.5-MoEOpen Weight
Released
Qwen1.5-MoE is an AI model released by Qwen on Thursday, Mar 28 2024, 53 days after Qwen1.5. It is an open-weight model — the trained weights are available to download and run. It is a 14.3B 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.. Benchmark results (shown below) cover HumanEval, MMLU, and GSM8K.
Get Qwen releases and AI news.
Every other Monday
Benchmarks
Coding
Reasoning & science
Compare Qwen1.5-MoE with
Suggested comparisons
Qwen1.5-MoEvsQwen4-MaxQwen1.5-MoEvsGPT-6.2 AstraQwen1.5-MoEvsClaude Fable 5.2Qwen1.5-MoEvsGemini 4 NeonQwen1.5-MoEvsMuse EmberQwen1.5-MoEvsGrok 4.7Qwen1.5-MoEvsDeepSeek-V4.1-Flash-1017Qwen1.5-MoEvsMistral Large 4Qwen1.5-MoEvsKimi K3.1 ProQwen1.5-MoEvsGLM-5.3-FlashQwen1.5-MoEvsNemotron 3.5 Bolt E4B 4GBAbout
Qwen1.5-MoE was Alibaba Cloud's first mixture-of-experts Qwen release. It arrived on March 28, 2024 with 14.3 billion total parameters and 2.7 billion active per token. The team built it by adapting the dense Qwen-1.8B checkpoint into a sparse model.
Qwen reported 62.5 on MMLU and 34.2 on HumanEval for the base checkpoint. The release tested whether a model could approach dense 7B performance with less computation per token, while the total weights still had to fit in memory.
Frequently asked questions
Qwen1.5-MoE was released by Qwen on Thursday, Mar 28 2024.