Modelpublic

RichardErkhov/PotatoB_-_Model_Kinship_2-1-gguf

sourceHugging Faceupdated 1y agoView on Hugging Face

0likes50downloads

Model Card

Quantization made by Richard Erkhov.

Request more models

ModelKinship2-1 - GGUF

—Model creator: https://huggingface.co/PotatoB/
—Original model: https://huggingface.co/PotatoB/ModelKinship2-1/

Name	Quant method	Size
Model_Kinship_2-1.Q2_K.gguf	Q2_K	2.53GB
Model_Kinship_2-1.IQ3_XS.gguf	IQ3_XS	2.81GB
Model_Kinship_2-1.IQ3_S.gguf	IQ3_S	2.96GB
Model_Kinship_2-1.Q3_K_S.gguf	Q3KS	2.95GB
Model_Kinship_2-1.IQ3_M.gguf	IQ3_M	3.06GB
Model_Kinship_2-1.Q3_K.gguf	Q3_K	3.28GB
Model_Kinship_2-1.Q3_K_M.gguf	Q3KM	3.28GB
Model_Kinship_2-1.Q3_K_L.gguf	Q3KL	3.56GB
Model_Kinship_2-1.IQ4_XS.gguf	IQ4_XS	3.67GB
Model_Kinship_2-1.Q4_0.gguf	Q4_0	3.83GB
Model_Kinship_2-1.IQ4_NL.gguf	IQ4_NL	3.87GB
Model_Kinship_2-1.Q4_K_S.gguf	Q4KS	3.86GB
Model_Kinship_2-1.Q4_K.gguf	Q4_K	4.07GB
Model_Kinship_2-1.Q4_K_M.gguf	Q4KM	4.07GB
Model_Kinship_2-1.Q4_1.gguf	Q4_1	4.24GB
Model_Kinship_2-1.Q5_0.gguf	Q5_0	4.65GB
Model_Kinship_2-1.Q5_K_S.gguf	Q5KS	4.65GB
Model_Kinship_2-1.Q5_K.gguf	Q5_K	4.78GB
Model_Kinship_2-1.Q5_K_M.gguf	Q5KM	4.78GB
Model_Kinship_2-1.Q5_1.gguf	Q5_1	5.07GB
Model_Kinship_2-1.Q6_K.gguf	Q6_K	5.53GB
Model_Kinship_2-1.Q8_0.gguf	Q8_0	7.17GB

Original model description: --- license: apache-2.0 tags:

—merge
—mergekit ---

This is an open model for iterative merging experiments.