File 002 · Local Intelligence
Record 011 · Runtimes · 2023
23.11.UGGUF
llama.cpp community
“A single-file model format that replaced a pile of .bin shards and Python glue.”
The file format of local LLMs.
GGUF succeeded GGML as the portable, metadata-rich container for quantized weights. Hugging Face became a GGUF storefront.
The interchange format the local ecosystem actually uses.
Filed notes
- Single-file quantized models
- Embedded metadata
- Cross-runtime portability
SIC
7372
Prepackaged Software
NAICS
511210
Software Publishers
