{
 "repo": "ggml-org/llama.cpp",
 "url": "https://github.com/ggml-org/llama.cpp",
 "what": "llama.cpp is a dependency-free C/C++ engine for running LLMs and vision language models locally or in the cloud, with quantization, many GPU backends, a CLI and an OpenAI-compatible server.",
 "language": "C++",
 "stars": null,
 "gain": null,
 "created": "",
 "uc_n": 3,
 "title": "llama.cpp",
 "show": true,
 "what_source": "deduped",
 "use_cases": "https://dedupedai.com/use-cases/ggml-org-llama-cpp/",
 "use_cases_json": "https://dedupedai.com/use-cases/r/ggml-org-llama-cpp.json",
 "json": "https://dedupedai.com/repos/r/ggml-org-llama-cpp.json",
 "slug": "ggml-org-llama-cpp",
 "api": "https://dedupedai.com/api/v1/repos/ggml-org-llama-cpp.json",
 "api_version": "v1"
}