Database · ai-tools
llama.cpp
llama.cpp is an open-source C++ implementation for running LLMs efficiently on CPU and GPU, enabling local AI inference.
Project
Overview
Foundational open-source project enabling efficient local LLM inference on consumer hardware.
Details
- Pricing model
- Open Source
- Platform
- CLI, Linux, macOS, Windows, Web
- Privacy relevance
- HIGH
- Strengths
- Efficient CPU inference, GGUF format, broad model support, active development, free
- Limitations
- Requires technical knowledge; no native UI; performance varies by hardware
- Last reviewed
- 2026-08-25