mradermacher/calme-3.2-instruct-78b-i1-GGUF

About

weighted/imatrix quants of https://huggingface.co/MaziyarPanahi/calme-3.2-instruct-78b

static quants are available at https://huggingface.co/mradermacher/calme-3.2-instruct-78b-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	24.4	for the desperate
GGUF	i1-IQ1_M	25.5	mostly desperate
GGUF	i1-IQ2_XXS	27.4
GGUF	i1-IQ2_XS	29.1
GGUF	i1-IQ2_S	30.0
GGUF	i1-IQ2_M	31.5
GGUF	i1-Q2_K	31.9	IQ3_XXS probably better
GGUF	i1-IQ3_XXS	34.1	lower quality
GGUF	i1-IQ3_XS	35.2
GGUF	i1-Q3_K_S	36.9	IQ3_XS probably better
GGUF	i1-IQ3_S	37.0	beats Q3_K*
GGUF	i1-IQ3_M	38.0
GGUF	i1-Q3_K_M	40.4	IQ3_S probably better
GGUF	i1-Q3_K_L	42.4	IQ3_M probably better
GGUF	i1-IQ4_XS	42.7
GGUF	i1-Q4_0	44.4	fast, low quality
GGUF	i1-Q4_K_S	47.0	optimal size/speed/quality
PART 1 PART 2	i1-Q4_K_M	50.8	fast, recommended
PART 1 PART 2	i1-Q5_K_S	55.2
PART 1 PART 2	i1-Q5_K_M	58.4
PART 1 PART 2	i1-Q6_K	69.1	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.