Pass IndexThe State of AISign in

llama.cpp

A small, dependency-free engine for running models on ordinary computers, including on a laptop's CPU.

how it works · the vocabulary

Ollamalocal inference

It made local models practical for people without a data-centre card, and its GGUF format is the de facto standard for distributing quantised weights. Ollama and most desktop apps are wrappers around it.

In the catalogue

Nearby

AgentAgent memoryAlignmentAutoregressiveBM25ChunkingCold startComputer use