CoolFace
Modelpublic

mradermacher/Triangulum-5B-it-i1-GGUF

sourceHugging Facecreativeml-openrail-mupdated 2y agoView on Hugging Face
0likes1.6kdownloads
Model Card

About

<!-- ### quantizeversion: 2 --> <!-- ### outputtensorquantised: 1 --> <!-- ### converttype: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/prithivMLmods/Triangulum-5B-it

<!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/Triangulum-5B-it-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_S1.6for the desperate
GGUFi1-IQ1_M1.7mostly desperate
GGUFi1-IQ2_XXS1.8
GGUFi1-IQ2_XS1.9
GGUFi1-IQ2_S2.0
GGUFi1-IQ2_M2.2
GGUFi1-Q2KS2.2very low quality
GGUFi1-Q2_K2.3IQ3_XXS probably better
GGUFi1-IQ3_XXS2.4lower quality
GGUFi1-IQ3_XS2.5
GGUFi1-Q3KS2.6IQ3_XS probably better
GGUFi1-IQ3_S2.7beats Q3_K*
GGUFi1-IQ3_M2.7
GGUFi1-Q3KM2.9IQ3_S probably better
GGUFi1-Q3KL3.1IQ3_M probably better
GGUFi1-IQ4_XS3.1
GGUFi1-Q4_03.3fast, low quality
GGUFi1-IQ4_NL3.3prefer IQ4_XS
GGUFi1-Q4KS3.3optimal size/speed/quality
GGUFi1-Q4KM3.5fast, recommended
GGUFi1-Q4_13.6
GGUFi1-Q5KS3.9
GGUFi1-Q5KM4.0
GGUFi1-Q6_K4.5practically 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 -->