# llama.cpp
Fast LLM inference in C/C++, the engine behind many local AI apps.
- Rank: #9 of 52 · #4 in Local AI
- Score: 68 (relative; maintenance 83, adoption 78, docs 29; community not measured)
- Safety: Caution — 12 critical-severity known vulnerabilities in runtime dependencies (OSV) (automated scan of commit 785322d on 2026-11-02, not a manual audit)
- Stars: 133105
- Last push: 2026-11-02
- License: MIT
- Repo: https://github.com/ggml-org/llama.cpp
- Fetched: 2026-11-02T06:08:26.085Z