CoolFace
Modelpublic

mradermacher/Babel-83B-Chat-i1-GGUF

sourceHugging Faceotherupdated 2y agoView on Hugging Face
3likes656downloads
Model Card

About

<!-- ### quantizeversion: 2 --> <!-- ### outputtensorquantised: 1 --> <!-- ### converttype: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/Tower-Babel/Babel-83B-Chat

<!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/Babel-83B-Chat-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)

LinkTypeSize/GBNotes
GGUFi1-IQ1_S26.0for the desperate
GGUFi1-IQ1_M27.2mostly desperate
GGUFi1-IQ2_XXS29.2
GGUFi1-IQ2_XS31.0
GGUFi1-IQ2_S32.0
GGUFi1-IQ2_M33.6
GGUFi1-Q2KS33.8very low quality
GGUFi1-Q2_K34.1IQ3_XXS probably better
GGUFi1-IQ3_XXS36.4lower quality
GGUFi1-IQ3_XS37.5
GGUFi1-Q3KS39.3IQ3_XS probably better
GGUFi1-IQ3_S39.4beats Q3_K*
GGUFi1-IQ3_M40.6
GGUFi1-Q3KM43.1IQ3_S probably better
GGUFi1-Q3KL45.3IQ3_M probably better
GGUFi1-IQ4_XS45.5
GGUFi1-Q4_047.4fast, low quality
PART 1 PART 2i1-Q4KS50.2optimal size/speed/quality
PART 1 PART 2i1-Q4_152.4
PART 1 PART 2i1-Q4KM54.3fast, recommended
PART 1 PART 2i1-Q5KS58.9
PART 1 PART 2i1-Q5KM62.4
PART 1 PART 2i1-Q6_K73.8practically like static Q6_K

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.

<!-- end -->