mradermacher/EXAONE-3.5-7.8B-Instruct-i1-GGUF

---

base_model: LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct language:

• en
• ko

library_name: transformers license: other license_link: LICENSE license_name: exaone quantized_by: mradermacher tags:

• lg-ai
• exaone
• exaone-3.5

---

About

weighted/imatrix quants of https://huggingface.co/LGAI-EXAONE/EXAONE-3.5-7.8B-Instruct

static quants are available at https://huggingface.co/mradermacher/EXAONE-3.5-7.8B-Instruct-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	2.0	for the desperate
GGUF	i1-IQ1_M	2.2	mostly desperate
GGUF	i1-IQ2_XXS	2.4
GGUF	i1-IQ2_XS	2.6
GGUF	i1-IQ2_S	2.7
GGUF	i1-IQ2_M	2.9
GGUF	i1-Q2K_S	3.0	very low quality
GGUF	i1-Q2K	3.2	IQ3XXS probably better
GGUF	i1-IQ3_XXS	3.3	lower quality
GGUF	i1-IQ3_XS	3.5
GGUF	i1-Q3KS	3.6	IQ3XS probably better
GGUF	i1-IQ3S	3.6	beats Q3K*
GGUF	i1-IQ3_M	3.7
GGUF	i1-Q3KM	4.0	IQ3S probably better
GGUF	i1-Q3KL	4.3	IQ3M probably better
GGUF	i1-IQ4_XS	4.4
GGUF	i1-Q404_4	4.6	fast on arm, low quality
GGUF	i1-Q404_8	4.6	fast on arm+i8mm, low quality
GGUF	i1-Q408_8	4.6	fast on arm+sve, low quality
GGUF	i1-Q4_0	4.6	fast, low quality
GGUF	i1-Q4K_S	4.6	optimal size/speed/quality
GGUF	i1-Q4K_M	4.9	fast, recommended
GGUF	i1-Q5K_S	5.5
GGUF	i1-Q5K_M	5.7
GGUF	i1-Q6K	6.5	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.