CoolFace
Modelpublic

mradermacher/c4ai-command-r-plus-08-2024-i1-GGUF

sourceHugging Facecc-by-nc-4.0updated 1y agoView on Hugging Face
1likes2.3kdownloads
Model Card

About

<!-- ### quantizeversion: 2 --> <!-- ### outputtensorquantised: 1 --> <!-- ### converttype: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/CohereLabs/c4ai-command-r-plus-08-2024

<!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/c4ai-command-r-plus-08-2024-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_S23.3for the desperate
GGUFi1-IQ1_M25.3mostly desperate
GGUFi1-IQ2_XXS28.7
GGUFi1-IQ2_XS31.7
GGUFi1-IQ2_S33.4
GGUFi1-IQ2_M36.1
GGUFi1-Q2_K39.6IQ3_XXS probably better
GGUFi1-IQ3_XXS40.8lower quality
GGUFi1-IQ3_XS43.7
GGUFi1-Q3KS46.0IQ3_XS probably better
GGUFi1-IQ3_S46.1beats Q3_K*
GGUFi1-IQ3_M47.8
PART 1 PART 2i1-Q3KM51.1IQ3_S probably better
PART 1 PART 2i1-Q3KL55.5IQ3_M probably better
PART 1 PART 2i1-IQ4_XS56.3
PART 1 PART 2i1-Q4_059.5fast, low quality
PART 1 PART 2i1-Q4KS59.7optimal size/speed/quality
PART 1 PART 2i1-Q4KM62.9fast, recommended
PART 1 PART 2i1-Q5KS71.9
PART 1 PART 2i1-Q5KM73.7
PART 1 PART 2i1-Q6_K85.3practically 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 -->