llama.cpp
⭐ 76.0k stars💬 text generation🔧 Cintermediate📄 MIT🔄 2026-06-29
About
LLM inference in C/C++ with GPU acceleration. Run quantized models efficiently on consumer hardware.
⚡ Quick Start
git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m model.gguf🏷️ Topics
💻 Supported Platforms
maclinuxwindows
📋 Technical Details
- Repository
- ggerganov/llama.cpp
- Language
- C
- License
- MIT
- Stars
- 76,000
- Category
- text generation
- Difficulty
- intermediate
- Last Updated
- 2026-06-29
- Platforms
- mac, linux, windows
Frequently Asked Questions About llama.cpp
What is llama.cpp?
LLM inference in C/C++ with GPU acceleration. Run quantized models efficiently on consumer hardware.
How do I install llama.cpp?
Run: git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m model.gguf
What are the system requirements for llama.cpp?
llama.cpp supports mac, linux, windows. It is written in C and is best suited for intermediate-level users. The repository has 76,000+ stars on GitHub and is licensed under MIT.