mradermacher/YanoljaNEXT-Rosetta-27B-2511-i1-GGUF

---

base_model: yanolja/YanoljaNEXT-Rosetta-27B-2511 language:

• ar
• bg
• zh
• cs
• da
• nl
• en
• fi
• fr
• de
• el
• gu
• he
• hi
• hu
• id
• it
• ja
• ko
• fa
• pl
• pt
• ro
• ru
• sk
• es
• sv
• tl
• th
• tr
• uk
• vi

library_name: transformers license: gemma mradermacher: readme_rev: 1 quantized_by: mradermacher tags:

• translation

---

About

weighted/imatrix quants of https://huggingface.co/yanolja/YanoljaNEXT-Rosetta-27B-2511

For a convenient overview and download list, visit our model page for this model.

static quants are available at https://huggingface.co/mradermacher/YanoljaNEXT-Rosetta-27B-2511-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	imatrix	0.1	imatrix file (for creating your own quants)
GGUF	i1-IQ1_S	6.8	for the desperate
GGUF	i1-IQ1_M	7.4	mostly desperate
GGUF	i1-IQ2_XXS	8.2
GGUF	i1-IQ2_XS	9.0
GGUF	i1-IQ2_S	9.5
GGUF	i1-IQ2_M	10.2
GGUF	i1-Q2K_S	10.3	very low quality
GGUF	i1-Q2K	11.1	IQ3XXS probably better
GGUF	i1-IQ3_XXS	11.4	lower quality
GGUF	i1-IQ3_XS	12.3
GGUF	i1-IQ3S	12.9	beats Q3K*
GGUF	i1-Q3KS	12.9	IQ3XS probably better
GGUF	i1-IQ3_M	13.3
GGUF	i1-Q3KM	14.1	IQ3S probably better
GGUF	i1-Q3KL	15.2	IQ3M probably better
GGUF	i1-IQ4_XS	15.6
GGUF	i1-Q4_0	16.5	fast, low quality
GGUF	i1-Q4K_S	16.6	optimal size/speed/quality
GGUF	i1-Q4K_M	17.4	fast, recommended
GGUF	i1-Q4_1	18.1
GGUF	i1-Q5K_S	19.8
GGUF	i1-Q5K_M	20.3
GGUF	i1-Q6K	23.4	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.