Artefact2
/

Mixtral-8x7B-Instruct-v0.1-GGUF

Model card Files Files and versions

Quants appear to be bigger

#1

by ayyylol - opened Apr 5, 2024

Hi,

Thanks for the quants! I was wondering if you know why, for example Q4_K_M in this repo is 28.4 GB but in TheBloke's repo it's 26.4 GB?

Just curious, thank you.

Owner Apr 8, 2024

Probably related to https://github.com/ggerganov/llama.cpp/pull/4872.

Thank you very much!

ayyylol changed discussion status to closed Apr 9, 2024

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment