OpenBMB 的 MiniCPM 获浏览器端本地 AI 聊天工具 moochy chat 支持
MiniCPM 获 moochy chat 支持
OpenBMB 的 MiniCPM 已在 moochy chat 中获得支持,该工具完全在浏览器标签页内本地运行,模型下载后无需联网。moochy chat 支持 CPU 或 GPU 推理,部分模型可达 150 tokens/s,无订阅、无 API key、100% 免费,基准测试中快于 WebLLM、wllama 和 Transformers.js。
OpenBMB· @OpenBMB · X·2026-11-18 09:15· 1 小时前AI 评分48
AI 导读
很高兴看到 MiniCPM 在 moochy chat 中获得支持!💙 完全本地化的 AI 直接在浏览器中运行,令人兴奋。做得好!🚀
正文 · 原文
Love seeing MiniCPM supported in moochy chat! 💙 Fully local AI right in the browser is exciting. Great work! 🚀
在 X 查看被引用的帖子As a continuation to this project, I'm currently working on something fun on top of it.
Introducing moochy chat: a local AI chat that runs entirely in your browser tab(CPU or GPU), meaning you don't need internet connection to use it after model gets downloaded in the browser tab.
got4 is < 54Kb of Web Assembly.
The page first load is 135Kb.For some models you can go up to 150 tokens per seconds.
No subscription, No API key, 100% free.
For now, faster than WebLLM(@mlc_ai_ ), wllama(@ngxson ) and Transformers.js(@xenovacom) on benchmarks.Models shipped right now are : @OpenBMB (MiniCPM), @Alibaba_Qwen, @MistralAI, @AIatMeta (Llama), @deepseek_ai, @huggingface (SmolLM)
#LocalLLM #WebGPU #BuildInPublic
来源:OpenBMB · x.com
来源:RadarAI · aihot.news