Local AI Glossary

What is GGUF (GPT-Generated Unified Format)?

Source: local-llm.net/glossary

The standard quantization format for llama.cpp and the broader local AI ecosystem. GGUF files are self-contained (including weights, tokenizer, and model configuration), support quantization levels from Q2 to Q8, and can run on CPU, NVIDIA GPU, AMD GPU, and Apple Silicon. The most universally supported format for local AI.

How GGUF (GPT-Generated Unified Format) fits in the local AI stack

GGUF (GPT-Generated Unified Format) is part of the broader local AI ecosystem. See the related guides, comparisons, and tools below to see how it applies in practice.

See also

Related terms