{
 "schema_version": 1,
 "generated": "2026-10-24",
 "repo": "ggml-org/llama.cpp",
 "name": "llama.cpp",
 "owner": "ggml-org",
 "slug": "ggml-org-llama-cpp",
 "github": "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.",
 "why": "132k stars, talked about in 2 AI sources we track",
 "language": "C++",
 "requirements": [
  "macOS, Linux or Windows",
  "Enough RAM or VRAM for the chosen GGUF model"
 ],
 "audience_note": "Developers who want to run open models locally on laptops, workstations or servers with minimal setup.",
 "risk": "none",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Software and DevOps",
 "url": "https://dedupedai.com/use-cases/ggml-org-llama-cpp/",
 "use_case_count": 3,
 "use_cases": [
  {
   "id": "ggml-org-llama-cpp--chat-with-local-model-from-hugging-face",
   "title": "Run an open model locally in one command",
   "best": true,
   "url": "https://dedupedai.com/use-cases/ggml-org-llama-cpp/chat-with-local-model-from-hugging-face/",
   "json": "https://dedupedai.com/use-cases/u/ggml-org-llama-cpp/chat-with-local-model-from-hugging-face.json"
  },
  {
   "id": "ggml-org-llama-cpp--serve-openai-compatible-local-api",
   "title": "Serve a local model behind an OpenAI-compatible API",
   "best": false,
   "url": "https://dedupedai.com/use-cases/ggml-org-llama-cpp/serve-openai-compatible-local-api/",
   "json": "https://dedupedai.com/use-cases/u/ggml-org-llama-cpp/serve-openai-compatible-local-api.json"
  },
  {
   "id": "ggml-org-llama-cpp--run-bigger-models-with-quantization",
   "title": "Fit a bigger model on limited hardware",
   "best": false,
   "url": "https://dedupedai.com/use-cases/ggml-org-llama-cpp/run-bigger-models-with-quantization/",
   "json": "https://dedupedai.com/use-cases/u/ggml-org-llama-cpp/run-bigger-models-with-quantization.json"
  }
 ],
 "disclaimer": "Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk."
}