bloom-1b7-i1-GGUF/README.md

base_model, language, library_name, license, quantized_by

base_model	language	library_name	license	quantized_by
bigscience/bloom-1b7	ak ar as bm bn ca code en es eu fon fr gu hi id ig ki kn lg ln ml mr ne nso ny or pa pt rn rw sn st sw ta te tn ts tum tw ur vi wo xh yo zh zhs zht zu	transformers	bigscience-bloom-rail-1.0	mradermacher

About

weighted/imatrix quants of https://huggingface.co/bigscience/bloom-1b7

static quants are available at https://huggingface.co/mradermacher/bloom-1b7-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	0.9	for the desperate
GGUF	i1-IQ1_M	0.9	mostly desperate
GGUF	i1-IQ2_XXS	1.0
GGUF	i1-IQ2_XS	1.0
GGUF	i1-IQ2_S	1.1
GGUF	i1-IQ2_M	1.1
GGUF	i1-Q2_K_S	1.1	very low quality
GGUF	i1-Q2_K	1.2	IQ3_XXS probably better
GGUF	i1-IQ3_XXS	1.2	lower quality
GGUF	i1-IQ3_XS	1.3
GGUF	i1-IQ3_S	1.3	beats Q3_K*
GGUF	i1-Q3_K_S	1.3	IQ3_XS probably better
GGUF	i1-IQ3_M	1.3
GGUF	i1-Q3_K_M	1.4	IQ3_S probably better
GGUF	i1-Q3_K_L	1.4	IQ3_M probably better
GGUF	i1-IQ4_XS	1.5
GGUF	i1-IQ4_NL	1.5	prefer IQ4_XS
GGUF	i1-Q4_0	1.5	fast, low quality
GGUF	i1-Q4_K_S	1.5	optimal size/speed/quality
GGUF	i1-Q4_K_M	1.6	fast, recommended
GGUF	i1-Q4_1	1.6
GGUF	i1-Q5_K_S	1.7
GGUF	i1-Q5_K_M	1.8
GGUF	i1-Q6_K	1.9	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.