mradermacher/llama3.1-405B-upscaled-603B-GGUF

About

static quants of https://huggingface.co/giannisan/llama3.1-405B-upscaled-603B

weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama3.1-405B-upscaled-603B-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	221.7
P1 P2 P3 P4 P5	IQ3_XS	246.6
P1 P2 P3 P4 P5 P6	Q3_K_S	260.3
P1 P2 P3 P4 P5 P6	IQ3_S	260.7	beats Q3_K*
P1 P2 P3 P4 P5 P6	IQ3_M	270.0
P1 P2 P3 P4 P5 P6	Q3_K_M	290.4	lower quality
P1 P2 P3 P4 P5 P6 P7	Q3_K_L	316.4
P1 P2 P3 P4 P5 P6 P7	IQ4_XS	325.0
P1 P2 P3 P4 P5 P6 P7	Q4_K_S	342.7	fast, recommended
P1 P2 P3 P4 P5 P6 P7 P8	Q4_K_M	361.7	fast, recommended
P1 P2 P3 P4 P5 P6 P7 P8 P9	Q5_K_S	415.3
P1 P2 P3 P4 P5 P6 P7 P8 P9	Q5_K_M	426.4
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11	Q6_K	495.2	very good quality
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11 P12 P13	Q8_0	641.3	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.