Demis Hassabis· @demishassabis · X·· 2026-04-03精选
AI 导读
Gemma 4 开源模型发布，提供 4 种尺寸：31B dense 版追求极致性能，26B MoE 版实现低延迟，2B 与 4B 版适配边缘设备，均可针对特定任务微调。
推荐理由
Google 发布 Gemma 4 开源模型，覆盖 2B 至 31B 多尺寸，支持端侧与 MoE 架构
正文 · 原文
Excited to launch Gemma 4: the best open models in the world for their respective sizes. Available in 4 sizes that can be fine-tuned for your specific task: 31B dense for great raw performance, 26B MoE for low latency, and effective 2B & 4B for edge device use - happy building! https://t.co/Sjbe3ph8xr
来源：Demis Hassabis · x.com