跳到正文
MiniMax (official)· @MiniMax_AI · X·· 2026-06-01AI 评分72
AI 导读

@cline 说得好 🔥 稀疏注意力将计算量降至前代的1/20。 现在可以在 Cline 上免费试用。

正文 · 原文

@cline put it well 🔥 sparse attention cutting compute to 1/20th the previous gen.

Try it for free on Cline right now

引用Cline@cline
The new MiniMax-M3 is their first model to have 1m context, multimodal, and agentic coding capability. Congratulations to @MiniMax_AI for the breakthrough in sparse-attention architecture cutting compute & cost to 1/20th their previous generation. Free to try in Cline now!
在 X 查看被引用的帖子

来源:MiniMax (official) · x.com