mradermacher/snowflake-arctic-instruct-i1-GGUF

About

weighted/imatrix quants of https://huggingface.co./Snowflake/snowflake-arctic-instruct

static quants are available at https://huggingface.co./mradermacher/snowflake-arctic-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
PART 1 PART 2 PART 3 PART 4	i1-Q2_K	173.7	IQ3_XXS probably better
PART 1 PART 2 PART 3 PART 4	i1-IQ3_XXS	183.5	lower quality
P1 P2 P3 P4 P5	i1-Q3_K_S	205.9	IQ3_XS probably better
P1 P2 P3 P4 P5	i1-IQ3_S	206.0	beats Q3_K*
P1 P2 P3 P4 P5	i1-IQ3_M	208.6
P1 P2 P3 P4 P5	i1-Q3_K_M	228.3	IQ3_S probably better
P1 P2 P3 P4 P5 P6	i1-Q3_K_L	247.2	IQ3_M probably better
P1 P2 P3 P4 P5 P6	i1-IQ4_XS	254.6
P1 P2 P3 P4 P5 P6	i1-Q4_0	270.6	fast, low quality
P1 P2 P3 P4 P5 P6	i1-Q4_K_S	271.7	optimal size/speed/quality
P1 P2 P3 P4 P5 P6	i1-Q4_K_M	289.3	fast, recommended
P1 P2 P3 P4 P5 P6 P7	i1-Q5_K_S	329.3
P1 P2 P3 P4 P5 P6 P7	i1-Q5_K_M	339.5
P1 P2 P3 P4 P5 P6 P7 P8	i1-Q6_K	392.8	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.