{"ok":true,"entity":{"slug":"llama-cpp","entityType":"product","name":"llama.cpp","officialName":"llama.cpp","canonicalName":"llama.cpp","displayName":"llama.cpp","category":"推論エンジン（OSS）","shortDescription":"C/C++で実装されたLLM推論エンジン。GGUF形式のモデルをGPUなしでもローカル環境で実行でき、オープンモデルをローカルで動かす基盤として広く使われる。","alias":["llama cpp"],"searchKeywords":["ローカルLLM","GGUF","推論エンジン","量子化"],"website":"https://github.com/ggml-org/llama.cpp","parentEntity":null,"primaryCluster":"ai-open-model","secondaryClusters":["ai-infrastructure"],"id":"llama-cpp","verificationStatus":"draft","updatedAt":"2026-07-18T11:08:14.467Z"},"referenceIndex":["P-01-001","P-02-001","P-04-001"]}