RichardErkhov/yhavinga_-_Boreas-7B-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Boreas-7B - GGUF

• Model creator: https://huggingface.co/yhavinga/
• Original model: https://huggingface.co/yhavinga/Boreas-7B/

Name	Quant method	Size
Boreas-7B.Q2_K.gguf	Q2_K	2.53GB
Boreas-7B.IQ3_XS.gguf	IQ3_XS	2.81GB
Boreas-7B.IQ3_S.gguf	IQ3_S	2.96GB
Boreas-7B.Q3_K_S.gguf	Q3_K_S	2.95GB
Boreas-7B.IQ3_M.gguf	IQ3_M	3.06GB
Boreas-7B.Q3_K.gguf	Q3_K	3.28GB
Boreas-7B.Q3_K_M.gguf	Q3_K_M	3.28GB
Boreas-7B.Q3_K_L.gguf	Q3_K_L	3.56GB
Boreas-7B.IQ4_XS.gguf	IQ4_XS	3.67GB
Boreas-7B.Q4_0.gguf	Q4_0	3.83GB
Boreas-7B.IQ4_NL.gguf	IQ4_NL	3.87GB
Boreas-7B.Q4_K_S.gguf	Q4_K_S	3.86GB
Boreas-7B.Q4_K.gguf	Q4_K	4.07GB
Boreas-7B.Q4_K_M.gguf	Q4_K_M	4.07GB
Boreas-7B.Q4_1.gguf	Q4_1	4.24GB
Boreas-7B.Q5_0.gguf	Q5_0	4.65GB
Boreas-7B.Q5_K_S.gguf	Q5_K_S	4.65GB
Boreas-7B.Q5_K.gguf	Q5_K	4.78GB
Boreas-7B.Q5_K_M.gguf	Q5_K_M	4.78GB
Boreas-7B.Q5_1.gguf	Q5_1	5.07GB
Boreas-7B.Q6_K.gguf	Q6_K	5.53GB

Original model description:

library_name: transformers tags: []

Model Card for Boreas-7B

Base model of Boreas-7B-chat For more info refer to the readme of the chat model.