跳到正文
@ArtificialAnlys· @ArtificialAnlys · X·· 29 天前AI 评分37
AI 导读

MiniCPM5-2B 在推理模型中同样具备 token 效率。它在每个 Artificial Analysis Intelligence Index 任务上使用 19k 输出 token,其中 11k 为推理 token,而 Ling 3.0 Tiny 为 56k,Granite 4.2 8B 为 33k。对于 2.6B 模型所面向的端侧和边缘部署而言,输出 token 用量至关重要。

正文

MiniCPM5-2B is also token-efficient for a reasoning model. It uses 19k output tokens per Artificial Analysis Intelligence Index task, 11k of them reasoning tokens, against 56k for Ling 3.0 Tiny and 33k for Granite 4.2 8B. Output token use matters for the on-device and edge deployments a 2.6B model targets.

来源:@ArtificialAnlys · x.com