# MiniCPM5-2B 联手 OpenMed 落地本地临床 AI

- 来源：OpenBMB (@OpenBMB)
- 发布时间：2026-09-17 22:00
- AIHOT 分数：31
- AIHOT 链接：https://aihot.news/items/cmu5ltl4r0az2roqorv1zw8n8
- 原文链接：https://x.com/OpenBMB/status/2100585575959154853

## AI 摘要

面壁智能 MiniCPM5-2B 与 OpenMed 合作，探索本地化临床 AI 工作流：由 MiniCPM5-2B 承担智能体层，调用工具、对比化验结果并生成带来源引用的临床交接记录。OpenMed 在模型处理前屏蔽敏感标识符并提取临床上下文，2B 规模模型可在资源受限硬件上本地推理。

## 正文

🏥 Bringing local agentic AI to healthcare with MiniCPM5-2B × OpenMed!

@OpenMed_AI paired OpenMed with MiniCPM5-2B to explore a local clinical AI workflow — combining privacy-preserving clinical data processing with a compact model capable of tool use, reasoning, and long-context understanding.

✨ Highlights:
🧠 MiniCPM5-2B powers the agent layer, calling tools, comparing lab results, and generating clinical handoffs with source references
🔒 OpenMed masks sensitive identifiers and extracts clinical context before the model processes the data
⚡ Compact 2B-scale model enables practical local inference on resource-constrained hardware
🛠️ Together, they demonstrate how open models can connect clinical data processing with agentic workflows while keeping inference on local hardware

It’s exciting to see MiniCPM5-2B move beyond standalone model benchmarks into real-world healthcare workflows — bringing tool use, reasoning, and local deployment together with OpenMed. 🙌

Built something with MiniCPM5-2B? Share your case with us! 🚀

🔗 GitHub: http://github.com/maziyarpanahi/openmed
🤗 Model: http://huggingface.co/openbmb/MiniCPM5-2B