mradermacher/airoboros-3_1-yi-34b-200k-i1-GGUF

---

basemodel: bhenrym14/airoboros-31-yi-34b-200k datasets:

• jondurbin/airoboros-3.1

language:

• en

library_name: transformers license: other license_link: LICENSE license_name: yi-license quantized_by: mradermacher

---

About

weighted/imatrix quants of https://huggingface.co/bhenrym14/airoboros-3_1-yi-34b-200k

static quants are available at https://huggingface.co/mradermacher/airoboros-3_1-yi-34b-200k-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	7.6	for the desperate
GGUF	i1-IQ1_M	8.3	mostly desperate
GGUF	i1-IQ2_XXS	9.4
GGUF	i1-IQ2_XS	10.4
GGUF	i1-IQ2_S	11.0
GGUF	i1-IQ2_M	11.9
GGUF	i1-Q2K_S	12.0	very low quality
GGUF	i1-Q2K	12.9	IQ3XXS probably better
GGUF	i1-IQ3_XXS	13.4	lower quality
GGUF	i1-IQ3_XS	14.3
GGUF	i1-Q3KS	15.1	IQ3XS probably better
GGUF	i1-IQ3S	15.1	beats Q3K*
GGUF	i1-IQ3_M	15.7
GGUF	i1-Q3KM	16.8	IQ3S probably better
GGUF	i1-Q3KL	18.2	IQ3M probably better
GGUF	i1-IQ4_XS	18.6
GGUF	i1-Q4_0	19.6	fast, low quality
GGUF	i1-Q4K_S	19.7	optimal size/speed/quality
GGUF	i1-Q4K_M	20.8	fast, recommended
GGUF	i1-Q4_1	21.7
GGUF	i1-Q5K_S	23.8
GGUF	i1-Q5K_M	24.4
GGUF	i1-Q6K	28.3	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.