CoolFace
Modelpublic

mradermacher/GigaChat3.1-702B-A36B-bf16-i1-GGUF

sourceHugging Facemitupdated 2mo agoView on Hugging Face
0likes21downloads
Model Card

About

<!-- ### quantizeversion: 2 --> <!-- ### outputtensorquantised: 1 --> <!-- ### converttype: hf --> <!-- ### vocabtype: --> <!-- ### tags: nicoboss --> <!-- ### quants: Q2K IQ3M Q4KS IQ3XXS Q3KM small-IQ4NL Q4KM IQ2M Q6K IQ4XS Q2KS IQ1M Q3KS IQ2XXS Q3KL IQ2XS Q5KS IQ2S IQ1S Q5KM Q40 IQ3XS Q41 IQ3S --> <!-- ### quantsskip: --> <!-- ### skip_mmproj: --> weighted/imatrix quants of https://huggingface.co/ai-sage/GigaChat3.1-702B-A36B-bf16

<!-- provided-files -->

*For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GigaChat3.1-702B-A36B-bf16-i1-GGUF).*

static quants are available at https://huggingface.co/mradermacher/GigaChat3.1-702B-A36B-bf16-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
GGUFimatrix1.1imatrix file (for creating your own quants)
PART 1 PART 2 PART 3i1-IQ1_S140.2for the desperate
PART 1 PART 2 PART 3 PART 4i1-IQ1_M156.2mostly desperate
PART 1 PART 2 PART 3 PART 4i1-IQ2_XXS182.9
P1 P2 P3 P4 P5i1-IQ2_XS204.4
P1 P2 P3 P4 P5i1-IQ2_S206.5
P1 P2 P3 P4 P5i1-IQ2_M227.8
P1 P2 P3 P4 P5i1-Q2KS235.9very low quality
P1 P2 P3 P4 P5 P6i1-Q2_K255.4IQ3_XXS probably better
P1 P2 P3 P4 P5 P6i1-IQ3_XXS269.9lower quality
P1 P2 P3 P4 P5 P6i1-IQ3_XS285.6
P1 P2 P3 P4 P5 P6 P7i1-IQ3_S302.6beats Q3_K*
P1 P2 P3 P4 P5 P6 P7i1-Q3KS302.6IQ3_XS probably better
P1 P2 P3 P4 P5 P6 P7i1-IQ3_M305.9
P1 P2 P3 P4 P5 P6 P7i1-Q3KM334.5IQ3_S probably better
P1 P2 P3 P4 P5 P6 P7 P8i1-Q3KL363.5IQ3_M probably better
P1 P2 P3 P4 P5 P6 P7 P8i1-IQ4_XS373.7
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10i1-Q4_0396.8fast, low quality
P1 P2 P3 P4 P5 P6 P7 P8 P9i1-Q4KS398.1optimal size/speed/quality
P1 P2 P3 P4 P5 P6 P7 P8 P9i1-Q4KM424.0fast, recommended
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10i1-Q4_1439.4
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10i1-Q5KS483.3
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11 P12i1-Q5KM497.9
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11 P12i1-Q6_K576.4practically 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 -->