Vibeleaderboard
← All Intel
Intel / article

Hy4 FP8 released

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

A 774B in FP8 lowers the memory needed to self-host a frontier-scale open model. It ships with vLLM and SGLang serving paths, under a custom Tencent license that needs checking before use.

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.
Read the source huggingface.co
More from Tencent model releases
Recommended reads
Comments

Checking sign-in…

Loading comments…