README.md

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama2-70b-v0.1 - GGUF

• Model creator: https://huggingface.co/hyeogi/
• Original model: https://huggingface.co/hyeogi/llama2-70b-v0.1/

Name	Quant method	Size
llama2-70b-v0.1.Q2_K.gguf	Q2_K	23.84GB
llama2-70b-v0.1.IQ3_XS.gguf	IQ3_XS	26.51GB
llama2-70b-v0.1.IQ3_S.gguf	IQ3_S	28.0GB
llama2-70b-v0.1.Q3_K_S.gguf	Q3_K_S	28.0GB
llama2-70b-v0.1.IQ3_M.gguf	IQ3_M	28.96GB
llama2-70b-v0.1.Q3_K.gguf	Q3_K	31.13GB
llama2-70b-v0.1.Q3_K_M.gguf	Q3_K_M	31.13GB
llama2-70b-v0.1.Q3_K_L.gguf	Q3_K_L	33.8GB
llama2-70b-v0.1.IQ4_XS.gguf	IQ4_XS	34.79GB
llama2-70b-v0.1.Q4_0.gguf	Q4_0	36.36GB
llama2-70b-v0.1.IQ4_NL.gguf	IQ4_NL	36.71GB
llama2-70b-v0.1.Q4_K_S.gguf	Q4_K_S	36.71GB
llama2-70b-v0.1.Q4_K.gguf	Q4_K	38.73GB
llama2-70b-v0.1.Q4_K_M.gguf	Q4_K_M	38.73GB
llama2-70b-v0.1.Q4_1.gguf	Q4_1	40.36GB
llama2-70b-v0.1.Q5_0.gguf	Q5_0	44.37GB
llama2-70b-v0.1.Q5_K_S.gguf	Q5_K_S	44.37GB
llama2-70b-v0.1.Q5_K.gguf	Q5_K	45.57GB
llama2-70b-v0.1.Q5_K_M.gguf	Q5_K_M	45.57GB
llama2-70b-v0.1.Q5_1.gguf	Q5_1	48.38GB
llama2-70b-v0.1.Q6_K.gguf	Q6_K	52.88GB
llama2-70b-v0.1.Q8_0.gguf	Q8_0	68.5GB

Original model description: Entry not found