CoolFace
Modelpublic

mradermacher/Dicephal-123B-i1-GGUF

sourceHugging Facellama2updated 2y agoView on Hugging Face
0likes62downloads
Model Card

About

weighted/imatrix quants of https://huggingface.co/ChuckMcSneed/Dicephal-123B

<!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/Dicephal-123B-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_S26.4for the desperate
GGUFi1-IQ2_XXS33.2
GGUFi1-IQ2_XS36.8
GGUFi1-IQ2_S38.6
GGUFi1-IQ2_M42.0
GGUFi1-Q2_K45.8IQ3_XXS probably better
GGUFi1-IQ3_XXS47.9lower quality
PART 1 PART 2i1-IQ3_XS50.8
PART 1 PART 2i1-Q3KS53.7IQ3_XS probably better
PART 1 PART 2i1-IQ3_S53.9beats Q3_K*
PART 1 PART 2i1-IQ3_M55.7
PART 1 PART 2i1-Q3KM59.9IQ3_S probably better
PART 1 PART 2i1-Q3KL65.2IQ3_M probably better
PART 1 PART 2i1-IQ4_XS66.4
PART 1 PART 2i1-Q4KS70.6optimal size/speed/quality
PART 1 PART 2i1-Q4KM74.6fast, recommended
PART 1 PART 2i1-Q5KS85.5
PART 1 PART 2i1-Q5KM87.8
PART 1 PART 2 PART 3i1-Q6_K101.9practically 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.

<!-- end -->