Modelpublic

artindnr/ChatBerry-i1-GGUF

sourceHugging Faceapache-2.0updated 1mo agoView on Hugging Face

1likes1.2kdownloads

Model Card

About

weighted/imatrix quants of https://huggingface.co/artindnr/ChatBerry

*For a convenient overview and download list, visit [model page for this model](https://hf.tst.eu/model#ChatBerry-i1-GGUF).*

static quants are available at https://huggingface.co/artindnr/ChatBerry-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	imatrix	0.1	imatrix file (for creating your own quants)
GGUF	i1-IQ1_M	12.1	mostly desperate
GGUF	i1-IQ1_S	12.1	for the desperate
GGUF	i1-IQ2_XXS	12.1
GGUF	i1-IQ2_XS	12.1
GGUF	i1-Q3KS	12.2	IQ3_XS probably better
GGUF	i1-IQ2_M	12.2
GGUF	i1-IQ2_S	12.2
GGUF	i1-IQ3_S	12.2	beats Q3_K*
GGUF	i1-IQ3_XS	12.2
GGUF	i1-IQ3_XXS	12.2	lower quality
GGUF	i1-Q2_K	12.2	IQ3_XXS probably better
GGUF	i1-IQ4_XS	12.2
GGUF	i1-Q2KS	12.2	very low quality
GGUF	i1-Q4_0	12.2	fast, low quality
GGUF	i1-IQ3_M	12.3
GGUF	i1-Q3KM	13.0	IQ3_S probably better
GGUF	i1-Q3KL	13.4	IQ3_M probably better
GGUF	i1-Q4_1	13.5
GGUF	i1-Q4KS	14.8	optimal size/speed/quality
GGUF	i1-Q4KM	15.9	fast, recommended
GGUF	i1-Q5KS	16.0
GGUF	i1-Q5KM	17.0
GGUF	i1-Q6_K	22.3	practically like static Q6_K

Original Repo

This is a copy from https://huggingface.co/mradermacher/ChatBerry-i1-GGUF