llama.cpp
Inference & Compute · Free + paid
LLM inference in C/C++ for local deployment
At a glance
- Made by
- ggml-org (GitHub organization)
- API
- Yes
- Available on
- CLI, API, Mac
- Open source
- MIT
- GitHub
- 131,110 stars · MIT
What is llama.cpp?
llama.cpp is a C/C++ project that aims to run LLM (and VLM) inference with state-of-the-art performance on a wide range of hardware with minimal setup. It is a pure C/C++ implementation with no dependencies and gives Apple silicon first-class support. It can be installed with an install script, Docker, prebuilt binaries, or a source build, and it can download models directly from Hugging Face and run them, or start an OpenAI-compatible API server with a built-in web UI.
- Pure C/C++ implementation with no dependencies
- First-class Apple silicon support
- Download and run Hugging Face models directly (llama cli)
- OpenAI-compatible API server (llama serve)
- Built-in web UI in llama serve
- Install via Docker, prebuilt binaries, or a source build
Who uses llama.cpp and for what
- Run LLM and VLM inference on a local PC or in the cloud
Pricing
Open source (free)
MIT 라이선스 오픈소스 C/C++ 추론 엔진, 직접 설치해 로컬·클라우드에서 실행, 요금 표기 없음
공식 페이지 확인 2026-10-14(산출 규칙 2026-10-15)
AI tools similar to llama.cpp (alternatives)
llama.cpp vs. alternatives at a glance
| AI | Pricing | Combos on the map | Connected tools | Free | Cheapest monthly | Korean |
|---|---|---|---|---|---|---|
| llama.cpp | Free + paid | 0 | 6 | — | — | — |
| ONNX Runtime | Free + paid | 0 | 6 | — | — | No |
| SGLang | Free + paid | 0 | 6 | — | — | No |
| Sol Engine | Free + paid | 0 | 6 | — | — | No |
| TensorRT | Free + paid | 0 | 6 | No | — | Yes |
0 of these 5 tools have a free plan.
Combo and connection counts are based on the relationships recorded on AI Galaxy Map (2026-10-26); they are not a quality ranking.
llama.cpp on AI Galaxy Map
- One of 43 AI tools in the Inference & Compute field.
- Connected to 6 other tools — #6 in its field.
Frequently asked questions
Can I use llama.cpp for free?
Open source (free). Prices can change, so check the official site before paying.
What AI can I use instead of llama.cpp?
Tools that do the same job, such as ONNX Runtime, SGLang, Sol Engine, TensorRT, are connected to it on the map.
Sources (official pages)
Checked on the official pages on 2026-10-14. Prices and features can change, so check the official site again before paying.