本地模型以支持家庭网络基础设施？
我在使用Claude Code管理我的家庭基础设施时感到非常兴奋。我一直以来都反对云计算，因此我不得不建立一个可以处理许多云功能的家庭设置。比如，我使用Resilio Sync来备份我家人的iOS照片，还有一个本地NAS来存储我合法下载并拥有的电影和电视节目。我还使用了一些树莓派，做一些本地的Home Assistant Z-Wave和Zigbee传感器。我的路由器、交换机和接入点都是UniFI，所有的摄像头、门铃和VoIP设备也是如此。总之，所有设备都是以本地为主（除了Talk，显然）。
如你所想，维护这些不同系统的熵需要时间，而我现在有了小孩，时间更是有限。所以当Claude Code发布时，我就像鱼入水一样迅速上手。我们映射了我的整个网络，我在所有设备上创建了账户，以便它可以通过SSH连接并配置一切（包括Ubiquiti Dream Machine Pro！）。我对它的故障排除和修复能力感到惊讶。
我有一台DGX Spark AI工作站（128GB内存），我现在真的想将工作交给一个本地模型，使用Opencode或Claude Code的工具，简单地指向一个通过API访问的vLLM实例化模型（只需将Opencode或Claude Code指向本地IP和API端点）。
这本来是可行的，但我刚刚尝试了Qwen3-coder，它因安全问题拒绝提供帮助。真让人沮丧。然后我尝试了GLM-4.7-Flash，但vLLM尚不支持，所以在我重建（请求Claude Code重建和部署）以尝试GLM-4.7-Flash与其他推理提供者之前，有没有人有用于基础设施维护的模型，而不是一个麻烦的家伙？如果没有开源的模型能帮忙，我可能最终会转向一个被彻底改造的模型。
查看原文
I have had a blast getting Claude Code to manage my home infrastructure. I have been against the cloud forever, so I have had to build a home setup that does a lot of cloud stuff. Like, I run Resillio Sync for all my family iOS photo backups, and a local NAS to host my legally downloaded and owned movies and tv shows, I also use a bunch of raspberry pis, doing things like running local Home Assistant z-wave and zigbee sensors. The router, switches, and APs are all UniFI, same with all the cameras, door bells, and VoIP. Again, all local first (except Talk, obvs).<p>As you can imagine, maintaining entropy for all these disparate systems takes time, of which I have less now that I have young kids. So when Claude Code was released, I took to it like a fish to water. We mapped my entire network, I created accounts on all the devices so it can SSH into everything and configure everything (including the Ubiquiti Dream Machine Pro!). I have been blow away at how well it troubleshoots and fixes everything.<p>I have a DGX Spark AI workstation (128gb of memory), and I really want to now hand off the work to a local model, either using Opencode or Claude Code harnesses and simply pointing at a vLLM instantiated model accessable by API (just point Opencode or Claude Code at the local IP and API endpoint).<p>It works, except I tried Qwen3-coder just now and it's refusing to help due to security concerns. Ugh. I then tried GLM-4.7-Flash, but vLLM doesn't support yet and so before I rebuild (ask Claude Code to rebuild and deploy) to try GLM.4-7-Flash with some other inference provider, does anyone have a model they use for infrastructure maintenance that isn't a little bitch? I will probably eventually go to an abliterated model if none of the open source ones will help.