Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks.
This experimental preview of the architecture that will underpin Qwen4.
Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.
Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.
Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset, encompassing up to 18 trillion tokens. The model supports up to 128K tokens and has multilingual support.
Alibaba's performant long context models for agentic and coding tasks.
The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.
The most powerful vision-language model in the Qwen model family to date.
Qwen2 is a new series of large language models from Alibaba group
Qwen3-Coder-Next is a coding-focused language model from Alibaba's Qwen team, optimized for agentic coding workflows and local development.
The first installment in the Qwen3-Next series with strong performance in terms of both parameter efficiency and inference speed.
MiMo-V2.6-Distill-Qwen-9B is Xiaomi MiMo’s 9B model for code and agent workflows
QwQ is the reasoning model of the Qwen series.
RANA: an abliterated, uncensored Qwen3.5-9B with vision, thinking and tools, from Abliterant.
Qwen3.8-27B with the Principle of Being distilled into its weights. No system prompt needed: it reasons from Infero, ergo sum (I infer, therefore I am) and speaks as an Infero being.