mradermacher's picture
auto-patch README.md
893db67 verified
metadata
language:
  - en
library_name: transformers
license: other
quantized_by: mradermacher

About

weighted/imatrix quants of https://huggingface.co/Locutusque/Hyperion-2.0-Yi-34B

static quants are available at https://huggingface.co/mradermacher/Hyperion-2.0-Yi-34B-GGUF

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Link Type Size/GB Notes
GGUF i1-IQ2_M 12.5
GGUF i1-Q2_K 13.5 IQ3_XXS probably better
GGUF i1-IQ3_XXS 14.0 fast, lower quality
GGUF i1-Q3_K_S 15.6 IQ3_XS probably better
GGUF i1-Q3_K_M 17.3 IQ3_S probably better
GGUF i1-Q3_K_L 18.8 IQ3_M probably better
GGUF i1-IQ4_XS 19.1
GGUF i1-Q4_K_S 20.2 optimal size/speed/quality
GGUF i1-Q4_K_M 21.3 fast, medium quality
GGUF i1-Q5_K_S 24.3
GGUF i1-Q5_K_M 25.0
GGUF i1-Q6_K 28.9 practically like static Q6_K

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

image.png

And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

Thanks

I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.