mradermacher/aquif-3-moe-17b-a2.8b-i1-GGUF

---

base_model: aquif-ai/aquif-3-moe-17B-A2.8B language:

• en

library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher tags:

• language
• aquif_moe
• text-generation-inference
• 17b
• qwen-like
• bailing-like
• science
• math
• code

---

About

weighted/imatrix quants of https://huggingface.co/aquif-ai/aquif-3-moe-17B-A2.8B

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

static quants are available at https://huggingface.co/mradermacher/aquif-3-moe-17b-a2.8b-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_M	5.7	mostly desperate
GGUF	i1-IQ2_XXS	6.2
GGUF	i1-IQ2_XS	6.5
GGUF	i1-IQ2_S	6.6
GGUF	i1-IQ2_M	6.9
GGUF	i1-Q2K	7.0	IQ3XXS probably better
GGUF	i1-Q2K_S	7.1	very low quality
GGUF	i1-IQ3_XXS	7.6	lower quality
GGUF	i1-IQ3_XS	7.7
GGUF	i1-Q3KS	8.1	IQ3XS probably better
GGUF	i1-IQ3S	8.1	beats Q3K*
GGUF	i1-IQ3_M	8.2
GGUF	i1-Q3KM	8.8	IQ3S probably better
GGUF	i1-Q3KL	9.2	IQ3M probably better
GGUF	i1-IQ4_XS	9.3
GGUF	i1-IQ4NL	9.6	prefer IQ4XS
GGUF	i1-Q4_0	9.7	fast, low quality
GGUF	i1-Q4K_S	10.3	optimal size/speed/quality
GGUF	i1-Q4_1	10.7
GGUF	i1-Q4K_M	11.3	fast, recommended
GGUF	i1-Q5K_S	12.0
GGUF	i1-Q5K_M	12.8
GGUF	i1-Q6K	15.2	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.