RichardErkhov/h2oai_-_h2ogpt-16k-codellama-13b-instruct-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

h2ogpt-16k-codellama-13b-instruct - GGUF

• Model creator: https://huggingface.co/h2oai/
• Original model: https://huggingface.co/h2oai/h2ogpt-16k-codellama-13b-instruct/

Name	Quant method	Size
h2ogpt-16k-codellama-13b-instruct.Q2_K.gguf	Q2_K	4.52GB
h2ogpt-16k-codellama-13b-instruct.IQ3_XS.gguf	IQ3_XS	4.99GB
h2ogpt-16k-codellama-13b-instruct.IQ3_S.gguf	IQ3_S	5.27GB
h2ogpt-16k-codellama-13b-instruct.Q3_K_S.gguf	Q3_K_S	2.71GB
h2ogpt-16k-codellama-13b-instruct.IQ3_M.gguf	IQ3_M	5.57GB
h2ogpt-16k-codellama-13b-instruct.Q3_K.gguf	Q3_K	4.26GB
h2ogpt-16k-codellama-13b-instruct.Q3_K_M.gguf	Q3_K_M	5.9GB
h2ogpt-16k-codellama-13b-instruct.Q3_K_L.gguf	Q3_K_L	6.45GB
h2ogpt-16k-codellama-13b-instruct.IQ4_XS.gguf	IQ4_XS	2.57GB
h2ogpt-16k-codellama-13b-instruct.Q4_0.gguf	Q4_0	6.86GB
h2ogpt-16k-codellama-13b-instruct.IQ4_NL.gguf	IQ4_NL	3.09GB
h2ogpt-16k-codellama-13b-instruct.Q4_K_S.gguf	Q4_K_S	2.28GB
h2ogpt-16k-codellama-13b-instruct.Q4_K.gguf	Q4_K	2.47GB
h2ogpt-16k-codellama-13b-instruct.Q4_K_M.gguf	Q4_K_M	1.55GB
h2ogpt-16k-codellama-13b-instruct.Q4_1.gguf	Q4_1	1.84GB
h2ogpt-16k-codellama-13b-instruct.Q5_0.gguf	Q5_0	0.7GB
h2ogpt-16k-codellama-13b-instruct.Q5_K_S.gguf	Q5_K_S	0.0GB
h2ogpt-16k-codellama-13b-instruct.Q5_K.gguf	Q5_K	0.0GB
h2ogpt-16k-codellama-13b-instruct.Q5_K_M.gguf	Q5_K_M	0.0GB
h2ogpt-16k-codellama-13b-instruct.Q5_1.gguf	Q5_1	0.0GB
h2ogpt-16k-codellama-13b-instruct.Q6_K.gguf	Q6_K	0.0GB
h2ogpt-16k-codellama-13b-instruct.Q8_0.gguf	Q8_0	0.0GB

Original model description:

license: llama2