deepseek_ai· @deepseek_ai · X·· 26 天前AI 评分
DeepSeek 发布 DeepSeek-V4.1-Flash 模型,主打更快推理与更高吞吐
DeepSeek 官方宣布推出 DeepSeek-V4.1-Flash,称其更智能、更快、更高效,是新架构家族中最小的模型,具备原生视觉理解能力。官方表示该模型面向更强能力、更快推理、更高吞吐而设计,并可扩展到更大模型。
🚀 Introducing DeepSeek-V4.1-Flash: smarter, faster, more efficient.
🔹 Introducing the smallest model in our new architecture family, with native visual understanding.
🔹 Designed for greater capability, faster inference, higher throughput, and scaling to larger models.
1/6
来源:deepseek_ai · x.com