CoolFace
Modelpublic

mradermacher/AceMath-72B-Instruct-i1-GGUF

sourceHugging Facecc-by-nc-4.0updated 2y agoView on Hugging Face
1likes889downloads
Model Card

About

<!-- ### quantizeversion: 2 --> <!-- ### outputtensorquantised: 1 --> <!-- ### converttype: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/nvidia/AceMath-72B-Instruct

<!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/AceMath-72B-Instruct-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_S22.8for the desperate
GGUFi1-IQ1_M23.8mostly desperate
GGUFi1-IQ2_XXS25.6
GGUFi1-IQ2_XS27.2
GGUFi1-IQ2_S28.0
GGUFi1-IQ2_M29.4
GGUFi1-Q2KS29.7very low quality
GGUFi1-Q2_K29.9IQ3_XXS probably better
GGUFi1-IQ3_XXS31.9lower quality
GGUFi1-IQ3_XS32.9
GGUFi1-IQ3_S34.6beats Q3_K*
GGUFi1-Q3KS34.6IQ3_XS probably better
GGUFi1-IQ3_M35.6
GGUFi1-Q3KM37.8IQ3_S probably better
GGUFi1-Q3KL39.6IQ3_M probably better
GGUFi1-IQ4_XS39.8
GGUFi1-Q4_041.5fast, low quality
GGUFi1-Q4KS44.0optimal size/speed/quality
GGUFi1-Q4_145.8
GGUFi1-Q4KM47.5fast, recommended
PART 1 PART 2i1-Q5KS51.5
PART 1 PART 2i1-Q5KM54.5
PART 1 PART 2i1-Q6_K64.4practically 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 -->