News for hackers. Stuff that matters.

A comment on Nvidia releases 8B model with learned 8x KV cache compression.

Re:Nvidia releases 8B model with learned 8x KV cache compres... by g023 on Saturday January 31, 2026 @04:46AM (#46835045)
I made a smaller sized version https://huggingface.co/g023/Qwen3-8B-DMS-8x-4bit-NF4
[ Parent | on HN ]

There are no comments on this comment yet.