Modelpublic

mradermacher/Marco-Mini-Instruct-i1-GGUF

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face

5likes1.8kdownloads

Model Card

About

weighted/imatrix quants of https://huggingface.co/ATH-MaaS/Marco-Mini-Instruct

*For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Marco-Mini-Instruct-i1-GGUF).*

static quants are available at https://huggingface.co/mradermacher/Marco-Mini-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)

Link	Type	Size/GB	Notes
GGUF	imatrix	0.2	imatrix file (for creating your own quants)
GGUF	i1-IQ1_S	3.7	for the desperate
GGUF	i1-IQ1_M	4.1	mostly desperate
GGUF	i1-IQ2_XXS	4.7
GGUF	i1-IQ2_XS	5.2
GGUF	i1-IQ2_S	5.3
GGUF	i1-IQ2_M	5.8
GGUF	i1-Q2KS	6.0	very low quality
GGUF	i1-Q2_K	6.5	IQ3_XXS probably better
GGUF	i1-IQ3_XXS	6.8	lower quality
GGUF	i1-IQ3_XS	7.2
GGUF	i1-IQ3_S	7.6	beats Q3_K*
GGUF	i1-Q3KS	7.6	IQ3_XS probably better
GGUF	i1-IQ3_M	7.7
GGUF	i1-Q3KM	8.4	IQ3_S probably better
GGUF	i1-Q3KL	9.1	IQ3_M probably better
GGUF	i1-IQ4_XS	9.3
GGUF	i1-IQ4_NL	9.9	prefer IQ4_XS
GGUF	i1-Q4_0	9.9	fast, low quality
GGUF	i1-Q4KS	10.0	optimal size/speed/quality
GGUF	i1-Q4KM	10.6	fast, recommended
GGUF	i1-Q4_1	10.9
GGUF	i1-Q5KS	12.0
GGUF	i1-Q5KM	12.4
GGUF	i1-Q6_K	14.3	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.