MoE models are large models that only activate a small fraction of their total parameters. Qwen 3.6 35B-A3B has 35 billion total parameters but only 3 billion active at inference time
混合专家(MoE)架构是本地模型能够高效运行的关键技术。初学者可能不理解为什么大模型能在普通硬件上运行，这正是因为MoE架构只激活部分参数。理解这一概念对于评估模型性能和硬件需求至关重要。