Google DeepMind 发布 Gemma 4 开放模型系列，主打智能体与多模态
原标题：Gemma 4: Byte for byte, the most capable open models
AI 摘要
Google DeepMind 发布了 Gemma 4 系列开放模型，包括 E2B、E4B、26B MoE 和 31B Dense 四种尺寸，支持高级推理、智能体工作流、多模态（视觉、音频）和 140 多种语言，采用 Apache 2.0 许可。该系列模型在 Arena AI 文本排行榜上表现优异，31B 模型排名第三，26B 模型排名第六，并针对从移动设备到 GPU 工作站等硬件进行了优化。
正文节选
Gemma 4: Byte for byte, the most capable open models Today, we are introducing Gemma 4 — our most intelligent open models to date. Purpose-built for advanced reasoning and agentic workflows, Gemma 4 delivers an unprecedented level of intelligence-per-parameter. This breakthrough builds on incredible community momentum: since the launch of our first generation, developers have downloaded Gemma over 400 million times, building a vibrant Gemmaverse of more than 100,000 variants. We listened closely