About

weighted/imatrix quants of https://huggingface.co/MaziyarPanahi/Supreme-Smaug-230B-v0.1

static quants are available at https://huggingface.co/mradermacher/Supreme-Smaug-230B-v0.1-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 50.0 for the desperate
PART 1 PART 2 i1-IQ1_M 54.3 mostly desperate
PART 1 PART 2 i1-IQ2_XXS 61.5
PART 1 PART 2 i1-IQ2_XS 67.9
PART 1 PART 2 i1-IQ2_S 72.9
PART 1 PART 2 i1-Q2_K_S 77.5 very low quality
PART 1 PART 2 i1-IQ2_M 78.7
PART 1 PART 2 i1-Q2_K 84.8 IQ3_XXS probably better
PART 1 PART 2 i1-IQ3_XXS 87.0 lower quality
PART 1 PART 2 i1-IQ3_XS 93.8
PART 1 PART 2 PART 3 i1-IQ3_S 99.1 beats Q3_K*
PART 1 PART 2 PART 3 i1-Q3_K_S 99.1 IQ3_XS probably better
PART 1 PART 2 PART 3 i1-IQ3_M 104.6
PART 1 PART 2 PART 3 i1-Q3_K_M 111.2 IQ3_S probably better
PART 1 PART 2 PART 3 i1-Q3_K_L 121.6 IQ3_M probably better
PART 1 PART 2 PART 3 i1-IQ4_XS 122.3
PART 1 PART 2 PART 3 i1-Q4_0 129.8 fast, low quality
PART 1 PART 2 PART 3 i1-Q4_K_S 130.3 optimal size/speed/quality
PART 1 PART 2 PART 3 i1-Q4_K_M 138.4 fast, recommended
PART 1 PART 2 PART 3 i1-Q4_1 143.7
PART 1 PART 2 PART 3 PART 4 i1-Q5_K_S 157.9
PART 1 PART 2 PART 3 PART 4 i1-Q5_K_M 162.6
PART 1 PART 2 PART 3 PART 4 i1-Q6_K 188.2 practically 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.

Downloads last month
13
GGUF
Model size
229B params
Architecture
llama
Hardware compatibility
Log In to view the estimation

1-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for mradermacher/Supreme-Smaug-230B-v0.1-i1-GGUF

Quantized
(1)
this model