On-Device & Local Inferencellama.cpp communityllama.cppMay 29, 2026Community

llama.cpp Discussion #23853 shares an NVFP4/MXFP6 mixed-precision tool

Discussion #23853 — released a tool for NVFP4/MXFP6 mixed precision + imatrix per-layer optimization. Comparisons shared in the discussion found NVFP4 faster but below Q4_K_M in quality

Why it matters

Real measurements showing hardware-native FP4 has not yet beaten community quantization. The format race is unresolved

Source — Primary sources first; secondary reports are labelled “Press”

Officialgithub.comhttps://github.com/ggml-org/llama.cpp/discussions/23853

Added in Week 35, 2026 · See that week

Same week

May 31NVIDIA's Vera Rubin NVL72 enters volume productionOfficial May 31NVIDIA releases the Isaac GR00T open humanoid reference designOfficial May 28Anthropic raises $65 billion in its Series HOfficial May 27Guni Sharon publishes Tree of Thoughts as a Classical Heuristic Search ProblemPaper

Nearby on the same axis

Jun 5, 2026Ollama 0.30 adds llama.cpp-based GGUF compatibility to its MLX engineOfficial May 19, 2026Google makes LiteRT-LM generally available (GA)Official Jun 9, 2026Apple expands the Foundation Models framework at WWDC 2026Press May 5, 2026Chrome 148 stable opens the Prompt API to the webOfficial