mradermacher/BigLlama-3.1-1T-Instruct-i1-GGUF

About

weighted/imatrix quants of https://huggingface.co/mlabonne/BigLlama-3.1-1T-Instruct

static quants are available at https://huggingface.co/mradermacher/BigLlama-3.1-1T-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
P1 P2 P3 P4 P5	i1-IQ1_S	214.1	for the desperate
P1 P2 P3 P4 P5	i1-IQ1_M	234.9	mostly desperate
P1 P2 P3 P4 P5 P6	i1-IQ2_XXS	269.5
P1 P2 P3 P4 P5 P6 P7	i1-IQ2_XS	299.8
P1 P2 P3 P4 P5 P6 P7	i1-IQ2_S	315.4
P1 P2 P3 P4 P5 P6 P7	i1-IQ2_M	343.0
P1 P2 P3 P4 P5 P6 P7 P8	i1-Q2_K	374.5	IQ3_XXS probably better
P1 P2 P3 P4 P5 P6 P7 P8	i1-IQ3_XXS	390.8	lower quality
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10	i1-IQ3_XS	416.4
P1 P2 P3 P4 P5 P6 P7 P8 P9	i1-Q3_K_S	438.8	IQ3_XS probably better
P1 P2 P3 P4 P5 P6 P7 P8 P9	i1-IQ3_S	440.2	beats Q3_K*
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10	i1-IQ3_M	455.9
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10	i1-Q3_K_M	490.0	IQ3_S probably better
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11	i1-Q3_K_L	534.1	IQ3_M probably better
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11 P12 P13	i1-IQ4_XS	543.7
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11 P12	i1-Q4_0	575.9	fast, low quality
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11 P12	i1-Q4_K_S	578.1	optimal size/speed/quality
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11 P12 P13	i1-Q4_K_M	610.5	fast, recommended
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11 P12 P13 P14 P15 P16	i1-Q5_K_S	700.9
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11 P12 P13 P14 P15	i1-Q5_K_M	719.8
P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11 P12 P13 P14 P15 P16 P17	i1-Q6_K	836.0	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.