clem 🤗· @ClementDelangue · X·2026-10-02 23:02· 3 小时前AI 评分41AI 导读决策模型现在可以在 llama.cpp 上端侧运行。免费、快速、私密! llama serve -hf ggml-org/Kev-4B-GGUF正文Decision models now run on device in llama.cpp. Free, fast, private!llama serve -hf ggml-org/Kev-4B-GGUF来源:clem 🤗 · x.com#产品更新#端侧#开源生态#Hugging Face查看事件全部后续