Qwen3 8B
Alibaba · 2025-04-29 · 8.2B parameters
Qwen3-8B is Alibaba's 8B open-weight dense model in the Qwen3 family, released April 29, 2025 under Apache 2.0. It supports a hybrid thinking/non-thinking mode for switching between chain-of-thought reasoning and direct response. Its context length is 32,768 tokens natively and has been validated up to 131,072 tokens with YaRN.