← AI tools directory

Self-hosted · LLM / chat

llama.cpp

Run GGUF models efficiently on CPU/GPU — foundation under many local tools.

Best for: Efficient local inference core

Pricing: Free (OSS)

Official site All tools

Strengths

Runs on modest hardware
Portable quant formats
Powers many UIs

Watch-outs

DIY build/flags
UI is separate

Appears in these stacks

Local / offline AI · supporting — Efficient GGUF core under many UIs.