mradermacher's picture
Upload README.md with huggingface_hub
34ed57e verified
|
raw
history blame
1.99 kB
metadata
language:
  - en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
  - moe

weighted/imatrix quants of https://huggingface.co./mistralai/Mixtral-8x7B-v0.1

Provided Quants

Link Type Size/GB Notes
GGUF i1-IQ1_S 9.7
GGUF i1-IQ2_XXS 12.5
GGUF i1-IQ2_XS 13.8
GGUF i1-Q2_K 17.5
GGUF i1-IQ3_XXS 18.5 fast, lower quality
GGUF i1-Q3_K_XS 19.2 IQ3-XXS probably better
GGUF i1-Q3_K_S 20.6 IQ3-XXS probably better
GGUF i1-Q3_K_M 22.7 lower quality
GGUF i1-Q3_K_L 24.3
GGUF i1-Q4_K_S 26.9 fast, medium quality
GGUF i1-Q4_K_M 28.6 fast, medium quality