Modelpublic

mradermacher/MXLewd-L2-20B-i1-GGUF

sourceHugging Facecc-by-nc-4.0updated 2y agoView on Hugging Face

3likes5.1kdownloads

Model Card

weighted/imatrix quants of https://huggingface.co/Undi95/MXLewd-L2-20B

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.

(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	4.7	for the desperate
GGUF	i1-IQ1_M	5.1	mostly desperate
GGUF	i1-IQ2_XXS	5.7
GGUF	i1-IQ2_XS	6.3
GGUF	i1-IQ2_S	6.7
GGUF	i1-IQ2_M	7.2
GGUF	i1-Q2_K	7.7	IQ3_XXS probably better
GGUF	i1-IQ3_XXS	7.9	lower quality
GGUF	i1-IQ3_XS	8.5
GGUF	i1-IQ3_S	9.0	beats Q3_K*
GGUF	i1-Q3KS	9.0	IQ3_XS probably better
GGUF	i1-IQ3_M	9.4
GGUF	i1-Q3KM	10.0	IQ3_S probably better
GGUF	i1-Q3KL	10.9	IQ3_M probably better
GGUF	i1-IQ4_XS	11.0
GGUF	i1-IQ4_NL	11.6	prefer IQ4_XS
GGUF	i1-Q4_0	11.6	fast, low quality
GGUF	i1-Q4KS	11.7	optimal size/speed/quality
GGUF	i1-Q4KM	12.3	fast, recommended
GGUF	i1-Q5KS	14.1
GGUF	i1-Q5KM	14.5
GGUF	i1-Q6_K	16.7	practically like static Q6_K

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.

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.