mradermacher/Aeonis-20b-i1-GGUF

---

base_model: athirdpath/Aeonis-20b language:

• en

library_name: transformers license: apache-2.0 quantized_by: mradermacher tags:

• not-for-all-audiences

---

About

weighted/imatrix quants of https://huggingface.co/athirdpath/Aeonis-20b

static quants are available at https://huggingface.co/mradermacher/Aeonis-20b-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	4.8	for the desperate
GGUF	i1-IQ1_M	5.2	mostly desperate
GGUF	i1-IQ2_XXS	5.9
GGUF	i1-IQ2_XS	6.4
GGUF	i1-IQ2_S	6.8
GGUF	i1-IQ2_M	7.3
GGUF	i1-Q2K	7.9	IQ3XXS probably better
GGUF	i1-IQ3_XXS	8.2	lower quality
GGUF	i1-IQ3_XS	8.7
GGUF	i1-Q3KS	9.1	IQ3XS probably better
GGUF	i1-IQ3S	9.2	beats Q3K*
GGUF	i1-IQ3_M	9.5
GGUF	i1-Q3KM	10.1	IQ3S probably better
GGUF	i1-Q3KL	10.9	IQ3M probably better
GGUF	i1-IQ4_XS	11.2
GGUF	i1-Q4_0	11.8	fast, low quality
GGUF	i1-Q4K_S	11.8	optimal size/speed/quality
GGUF	i1-Q4K_M	12.5	fast, recommended
GGUF	i1-Q5K_S	14.2
GGUF	i1-Q5K_M	14.6
GGUF	i1-Q6K	16.9	practically like static Q6K

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.