Settings

Theme

Nvidia releases 8B model with learned 8x KV cache compression

huggingface.co

8 points by alecco 5 days ago · 4 comments

Reader

aleccoOP 5 days ago

The paper behind it was presented in December 2025 Neurips

Release thread: https://xcancel.com/p_nawrot/status/2014770473289019709

Slides and audio presentation: https://neurips.cc/virtual/2025/loc/san-diego/poster/119605

vercaemert 5 days ago

I'd be interested to hear some use cases people have for large contexts on an 8B model. Other than sentiment analysis or summarization (this release implies agentic use). My experience with the general intelligence of agentic interactions is that everything is unusable before 32B for any context greater than 4k tokens.

  • WaalkTheEaarth 2 days ago

    I personally use a 8B model for general use on my laptop lol, it works like a charm and makes sense (most of the time atleast)

Keyboard Shortcuts

j
Next item
k
Previous item
o / Enter
Open selected item
?
Show this help
Esc
Close modal / clear selection