The NVFP4 build reduces memory requirements for self-hosting Meta's 816B (42B active) open weightsA model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.Full definition → model, with Transformers and vLLM instructions.
Terms in this piece · Glossary
quantization — Shrinking a model by storing its numbers less precisely — like rounding — so it runs faster and fits on smaller hardware, at a small quality cost.
multimodal — A model that works with more than text — reading images, audio, or video, and sometimes generating them too.
mixture-of-experts — A model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
