Projects
llama.cpp
Open-source engine for running language models on personal computers
4recordsFirst record 2023Latest May 29, 2026
Records 4
Newest first. Open one to see it with its source.
llama.cpp community
llama.cpp Discussion #23853 shares an NVFP4/MXFP6 mixed-precision tool
Real measurements showing hardware-native FP4 has not yet beaten community quantization. The format race is unresolved
On-Device & Local InferenceOfficial
llama.cpp (ggml-org)
llama.cpp merges PR #19769, adding NVFP4
GGUF absorbed a hardware-native FP4 format beyond its own K-quants
On-Device & Local InferenceOfficial
llama.cpp community
NVFP4 support requested in llama.cpp Discussion #16668
The point at which the path was set for GGUF to absorb vendor FP4 formats one after another
On-Device & Local InferenceOfficial
llama.cpp community
llama.cpp community introduces the GGUF format
A single-file distribution format with metadata and backward compatibility — the container image of local model distribution