开源权重周报：V4.1-Flash 等三模型均无独立 GitHub 仓库
作者盘点 60 个开源权重编程模型与运行工具，指出本周发布的 DeepSeek V4.1-Flash 等三个模型都没有自己的 GitHub 仓库，真正该学的是 Ollama、llama.cpp 等运行时。
Three open-weight models dropped this week: Reflection's Beam, DeepSeek V4.1-Flash, Liquid's LFM2.5-24B. None of them has its own GitHub repo. That one detail changed how I think about "keeping up" with local AI. I keep a list of open-weight coding models + the tools to run them, ranked by GitHub stars. 60 entries. The top of the board isn't a model. It's Ollama (183.7k) and llama.cpp (131.6k). 💡 The model repos that do exist are basically weight cards. DeepSeek-V3: 104.5k stars, last updated Aug 2025. It doesn't need commits. The weights are the product. Ollama, llama.cpp, vLLM, SGLang? All pushed yesterday. So here's my take: stop chasing every model drop. Models rotate weekly (literally, this week). The runtime is the thing you actually learn, configure and debug. Beam shipped with day-0 vLLM and SGLang support for a reason. Not gonna lie, the entry that surprised me most: a repo that says it runs a 2.78T-param Kimi K3 on one CPU in 8.24 GB of RAM. 9.1k stars. The list (CC0, ranked by stars, updated 10-18): https://github.com/MaxonT/top-open-weight-coding-models