mradermacher's picture
Upload README.md with huggingface_hub
cdf85f9 verified
|
raw
history blame
2.1 kB
metadata
language:
  - en
library_name: transformers
license: llama2
quantized_by: mradermacher

weighted/imatrix quants of https://huggingface.co/sophosympatheia/Aurora-Nights-70B-v1.0

Provided Quants

Link Type Size/GB Notes
GGUF i1-IQ1_S 14.9
GGUF i1-IQ2_XXS 18.6
GGUF i1-IQ2_XS 20.7
GGUF i1-Q2_K 25.8
GGUF i1-IQ3_XXS 27.3 fast, lower quality
GGUF i1-Q3_K_XS 28.6 IQ3-XXS probably better
GGUF i1-Q3_K_S 30.2 IQ3-XXS probably better
GGUF i1-Q3_K_M 33.6 lower quality
GGUF i1-Q3_K_L 36.5
GGUF i1-Q4_K_S 39.6 fast, medium quality
GGUF i1-Q4_K_M 41.7 fast, medium quality