NVFP4 support requested in llama.cpp Discussion #16668
AIMade by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made
NVFP4 support requested in Discussion #16668. A maintainer pointed to the MXFP4 support PR as the template
Why it matters
The point at which the path was set for GGUF to absorb vendor FP4 formats one after another
Source — Primary sources first; secondary reports are labelled “Press”
Officialgithub.comhttps://github.com/ggml-org/llama.cpp/discussions/16668Added in Week 35, 2026 · See that week
On the map — ⑲ On-Device line
- Previous stopOllama previews cloud
- This recordNVFP4 support requested in llama.cpp Discussion #16668
- Next stopApple publishes M5 GPU Neural Accelerator + MLX benchmarks