llama.cpp
github.com/ggml-org/llama.cpp- Category
- AI Tools
- Pricing
- Open Source
- Type
- TOOL
- Builder
- ggml-org
- GitHub
- 121.6k stars
- Added
- Apr 14, 2026
About
A C/C++ library for running large language models locally with minimal setup and optimized performance across different hardware architectures. Enables LLM inference on CPUs and GPUs with various quantization options to reduce memory usage.
Why it made the leaderboard
Run large language models locally with minimal setup — a plain C/C++ engine with quantization options that shrink memory use and optimized inference across CPUs, GPUs, and hardware architectures.
Tags
llminferencecppquantizationlocal-aiggmlgpucpu
Tech Stack
Python
Media
Comments (0)
No comments yet
Indexed by a proprietary survey. Corrections welcome.