{"as_of":"2026-10-12","license":"CC-BY-4.0","license_url":"https://creativecommons.org/licenses/by/4.0/","cite_as":"The Local Bench (thelocalbench.com), data as of 2026-10-12, CC BY 4.0","source_url":"https://thelocalbench.com","tool":{"slug":"llama-cpp","name":"llama.cpp","category":"Runtimes","subcategory":"Inference engine","summary":{"value":"The C/C++ inference engine behind GGUF; ships llama-server with an OpenAI-compatible API.","flag":"sourced","source":"https://github.com/ggml-org/llama.cpp","note":"Our one-line paraphrase of the official description."},"website":"https://llama.app","repo":"https://github.com/ggml-org/llama.cpp","archived":false,"open_source":{"value":true,"license":"MIT","restrictive":false,"flag":"verified","source":"https://github.com/ggml-org/llama.cpp/blob/HEAD/LICENSE"},"pricing":{"model":"free","starting_usd":0,"range":null,"flag":"verified","source":"https://github.com/ggml-org/llama.cpp","note":"Free and open source to self-host."},"local_support":{"ollama":{"value":null,"flag":"not_measured","source":null,"note":"Not found in the official README or docs we checked."},"llamacpp":{"value":true,"flag":"sourced","source":"https://github.com/ggml-org/llama.cpp#readme","note":"Mentioned in the official README."},"lmstudio":{"value":null,"flag":"not_measured","source":null,"note":"Not found in the official README or docs we checked."},"openai":{"value":true,"flag":"sourced","source":"https://github.com/ggml-org/llama.cpp#readme","note":"Mentioned in the official README."},"mcp":{"value":null,"flag":"not_measured","source":null,"note":"Not found in the official README or docs we checked."}},"platforms":{"value":["macOS","Linux","Docker"],"flag":"sourced","source":"https://github.com/ggml-org/llama.cpp#readme"},"logo":{"file":"/logos/tools/llama-cpp.webp","source_kind":"github-org-avatar","source_url":"https://github.com/ggml-org.png?size=384","official_site":"https://llama.app","checked":"2026-10-13","note":"Trademark of its owner; shown only to identify the tool."},"date_added":"2026-10-13","last_verified":"2026-10-13","sponsor":{"sponsored":false,"disclosure":null,"relationship":null},"page":"https://thelocalbench.com/tools/llama-cpp","markdown":"https://thelocalbench.com/tools/llama-cpp.md","json":"https://thelocalbench.com/api/v1/tools/llama-cpp.json"},"json_ld":{"@context":"https://schema.org","@type":"SoftwareApplication","name":"llama.cpp","url":"https://llama.app","sameAs":["https://github.com/ggml-org/llama.cpp"],"description":"The C/C++ inference engine behind GGUF; ships llama-server with an OpenAI-compatible API.","applicationCategory":"DeveloperApplication","applicationSubCategory":"Runtimes: Inference engine","operatingSystem":"macOS, Linux, Docker","license":"MIT","isAccessibleForFree":true,"offers":{"@type":"Offer","price":0,"priceCurrency":"USD","description":"Free"},"dateModified":"2026-10-13"}}