mradermacher/DeepSeek-V3-GGUF

About

static quants of https://huggingface.co/deepseek-ai/DeepSeek-V3

weighted/imatrix quants are available at https://huggingface.co/mradermacher/DeepSeek-V3-i1-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
P1 P2 P3 P4 P5	Q2_K	244.1
P1 P2 P3 P4 P5 P6	Q3_K_S	289.2
P1 P2 P3 P4 P5 P6 P7	Q3_K_M	319.3	lower quality
P1 P2 P3 P4 P5 P6 P7 P8	Q3_K_L	347.5
P1 P2 P3 P4 P5 P6 P7 P8	IQ4_XS	359.6
P1 P2 P3 P4 P5 P6 P7 P8	Q4_K_S	380.1	fast, recommended
P1 P2 P3 P4 P5 P6 P7 P8 P9	Q4_K_M	404.5	fast, recommended
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10	Q5_K_S	461.9
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10	Q5_K_M	475.5
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11 P12	Q6_K	550.9	very good quality
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11 P12 P13 P14 P15 P16 P17 P18	Q8_0	713.4	fast, best quality

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.