Modelpublic

mradermacher/Endurance-100B-v1.1-i1-GGUF

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes132downloads

Model Card

About

weighted/imatrix quants of https://huggingface.co/TheDrummer/Endurance-100B-v1.1

static quants are available at https://huggingface.co/mradermacher/Endurance-100B-v1.1-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	21.4	for the desperate
GGUF	i1-IQ1_M	23.4	mostly desperate
GGUF	i1-IQ2_XXS	26.7
GGUF	i1-IQ2_XS	29.7
GGUF	i1-IQ2_S	31.6
GGUF	i1-Q2KS	34.2	very low quality
GGUF	i1-IQ2_M	34.2
GGUF	i1-Q2_K	37.2	IQ3_XXS probably better
GGUF	i1-IQ3_XXS	38.6	lower quality
GGUF	i1-IQ3_XS	41.2
GGUF	i1-Q3KS	43.4	IQ3_XS probably better
GGUF	i1-IQ3_S	43.6	beats Q3_K*
GGUF	i1-IQ3_M	45.4
GGUF	i1-Q3KM	48.5	IQ3_S probably better
PART 1 PART 2	i1-Q3KL	53.0	IQ3_M probably better
PART 1 PART 2	i1-IQ4_XS	53.7
PART 1 PART 2	i1-Q4_0	56.9	fast, low quality
PART 1 PART 2	i1-Q4KS	57.1	optimal size/speed/quality
PART 1 PART 2	i1-Q4KM	60.1	fast, recommended
PART 1 PART 2	i1-Q4_1	63.0
PART 1 PART 2	i1-Q5KS	69.2
PART 1 PART 2	i1-Q5KM	71.0
PART 1 PART 2	i1-Q6_K	82.5	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

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.