Vibeleaderboard
← All Intel
Intel / article

Xing4.1 Preview released

Source
huggingface.co
Author
XingChen model releases
Date
Why it matters

An openly licensed sparse with 1M and roughly 17B active parameters targets agentic coding at lower serving cost. Engineers choosing self-hosted models can evaluate it against other options.

Terms in this piece · Glossary
  • 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.
  • attention — The mechanism that lets a model weigh which earlier words matter for the word it's currently processing — the core operation of a transformer.
  • Context and context window — Context is the information available for a generation; the context window is the capacity available to hold it.
  • Open weights — A model whose learned parameter values have been made available to download, under terms the publisher sets.
Read the source huggingface.co
Recommended reads
Comments

Checking sign-in…

Loading comments…