JuheNext

Qwen3-235B-A22B, part of the cutting-edge Qwen3 series, introduces the next generation of large language models with both dense and mixture-of-experts (MoE) architectures. This advanced model enables seamless switching between thinking mode (for complex reasoning, math, and coding) and non-thinking mode (for fast, general-purpose dialogue) within a single model—delivering optimal performance for a wide range of applications.

Qwen3-32B is a state-of-the-art large language model from the Qwen series, featuring seamless mode switching for both advanced reasoning and efficient dialogue, superior alignment with human preferences, leading agent integration, and robust multilingual support.

Qwen3-30B-A3B-FP8 is a state-of-the-art large language model in the Qwen3 series, offering advanced reasoning, seamless mode-switching, strong agent capabilities, and multilingual support with 30.5B parameters.