mradermacher's picture
auto-patch README.md
2e9641a verified
|
raw
history blame
4.47 kB
metadata
base_model: TheSkullery/BA-Zephyria-39b
language:
  - en
library_name: transformers
quantized_by: mradermacher
tags:
  - mergekit
  - merge

About

weighted/imatrix quants of https://huggingface.co/TheSkullery/BA-Zephyria-39b

static quants are available at https://huggingface.co/mradermacher/BA-Zephyria-39b-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-IQ1_S 8.5 for the desperate
GGUF i1-IQ1_M 9.2 mostly desperate
GGUF i1-IQ2_XXS 10.5
GGUF i1-IQ2_XS 11.7
GGUF i1-IQ2_S 12.4
GGUF i1-IQ2_M 13.4
GGUF i1-Q2_K 14.5 IQ3_XXS probably better
GGUF i1-IQ3_XXS 15.1 lower quality
GGUF i1-Q3_K_S 17.0 IQ3_XS probably better
GGUF i1-IQ3_M 17.7
GGUF i1-Q3_K_M 18.9 IQ3_S probably better
GGUF i1-Q3_K_L 20.6 IQ3_M probably better
GGUF i1-IQ4_XS 21.0
GGUF i1-Q4_K_S 22.3 optimal size/speed/quality
GGUF i1-Q4_K_M 23.5 fast, recommended
GGUF i1-Q5_K_S 27.0
GGUF i1-Q5_K_M 27.7
GGUF i1-Q6_K 32.1 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

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.

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. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.