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.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
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.
Why it matters
Text diffusion at 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 → scale, with up to 4x faster generation on GPU — it opens speed-critical local and interactive workflows where tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition →-by-token decoding was the bottleneck.
