# 面壁智能赞 MiniCPM5-2B 本地证据地图应用

- 来源：OpenBMB (@OpenBMB)
- 发布时间：2026-09-08 21:47
- AIHOT 分数：33
- AIHOT 链接：https://aihot.news/items/cmtsquxrt02fkrokalipfjbw4
- 原文链接：https://x.com/OpenBMB/status/2097321040695509337

## AI 摘要

面壁智能 OpenBMB 称赞 @aijoey 将 MiniCPM5-2B 作为本地 worker，在 DGX Spark 上构建证据地图应用 Footnote。该 2B 模型完成从 21 个来源提取 31 条主张并连接推理的全部工作，且支持增量更新。面壁智能称这正是其期望的端侧智能体负载。

## 正文

Great real-world example. @aijoey is using MiniCPM5-2B as local workers to extract quoted findings and build a living evidence map (Footnote app) — all from a 2B model running on DGX Spark.
21 sources → 31 claims → connected reasoning, with the ability to incrementally update the map. This is exactly the kind of practical, on-device agentic workload we hoped MiniCPM5-2B could support. Impressive work!

### 引用推文

> Joey：Been putting MiniCPM5-2B to work on my DGX Spark. Built an app called Footnote that turns a research question into a living map of evidence. The setup: • Astra ...