{"provider_url":"https://hatena.blog","title":"llama.cpp\u306e\u958b\u767a\u5143\u304cHugging Face\u306b\u5408\u6d41 \u2015 GGUF\u30fbOllama\u30fbLM Studio\u3078\u306e\u5f71\u97ff\u3092\u8003\u3048\u308b","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fuepon.hatenadiary.com%2Fentry%2F2026%2F02%2F24%2F122434\" title=\"llama.cpp\u306e\u958b\u767a\u5143\u304cHugging Face\u306b\u5408\u6d41 \u2015 GGUF\u30fbOllama\u30fbLM Studio\u3078\u306e\u5f71\u97ff\u3092\u8003\u3048\u308b - uepon\u65e5\u3005\u306e\u5099\u5fd8\u9332\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","width":"100%","categories":["AI","LLM","\u30b3\u30f3\u30d4\u30e5\u30fc\u30bf"],"blog_title":"uepon\u65e5\u3005\u306e\u5099\u5fd8\u9332","image_url":null,"published":"2026-02-24 12:24:34","height":"190","type":"rich","provider_name":"Hatena Blog","blog_url":"https://uepon.hatenadiary.com/","author_name":"ueponx","author_url":"https://blog.hatena.ne.jp/ueponx/","description":"2026\u5e742\u6708\u3001\u30ed\u30fc\u30ab\u30ebLLM\u3092\u89e6\u3063\u3066\u3044\u308b\u4eba\u306b\u3068\u3063\u3066\u306f\u304b\u306a\u308a\u5927\u304d\u306a\u30cb\u30e5\u30fc\u30b9\u304c\u3042\u308a\u307e\u3057\u305f\u3002 llama.cpp\u306e\u5275\u8a2d\u8005\u3067\u3042\u308bGeorgi Gerganov\u7387\u3044\u308bggml.ai\u304c\u3001Hugging Face\u306b\u5408\u6d41\u3059\u308b\u3068\u3044\u3046\u3082\u306e\u3067\u3059\u3002 Hugging Face\u516c\u5f0f\u30d6\u30ed\u30b0\u3067\u306f\u3053\u3046\u66f8\u304b\u308c\u3066\u3044\u307e\u3059\u3002 We are super happy to announce that GGML, creators of Llama.cpp, are joining HF in order to keep future AI open. llama.cpp is the fundamental building block\u2026","version":"1.0","url":"https://uepon.hatenadiary.com/entry/2026/02/24/122434"}