约 14MB 内存运行 2.7 亿参数模型:谷歌工程师把 AI 装进打印机,每词元耗时约 60 秒
Source IT之家2h ago
Summary
This item is a 中文-language original; headline and summary shown as published.
IT之家 11 月 20 日消息,谷歌 DeepMind 技术团队成员奥马尔 · 圣塞维耶罗(Omar Sanseviero)于 11 月 17 日在 X 平台发布推文,在只占用 14.1MB 内存的情况下, 成功让办公激光打印机运行 2.7 亿参数的 Gemma 3 270M 模型,每输出一个词元(Token)消耗…
We index headlines and summaries only. Full content and copyright remain with the original publisher — follow the source link to read it.
Open original- Desk
- Tech
- Region
- China
- Language
- 中文
- Item ID
- tech-ba7ce141
Comments 0 comments
No comments yet. Be the first.