RichardErkhov/hanseungwook_-_vas-tiny-llama-1.1b-hh-sft-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

vas-tiny-llama-1.1b-hh-sft - GGUF

• Model creator: https://huggingface.co/hanseungwook/
• Original model: https://huggingface.co/hanseungwook/vas-tiny-llama-1.1b-hh-sft/

Name	Quant method	Size
vas-tiny-llama-1.1b-hh-sft.Q2_K.gguf	Q2_K	0.4GB
vas-tiny-llama-1.1b-hh-sft.Q3_K_S.gguf	Q3_K_S	0.47GB
vas-tiny-llama-1.1b-hh-sft.Q3_K.gguf	Q3_K	0.51GB
vas-tiny-llama-1.1b-hh-sft.Q3_K_M.gguf	Q3_K_M	0.51GB
vas-tiny-llama-1.1b-hh-sft.Q3_K_L.gguf	Q3_K_L	0.55GB
vas-tiny-llama-1.1b-hh-sft.IQ4_XS.gguf	IQ4_XS	0.57GB
vas-tiny-llama-1.1b-hh-sft.Q4_0.gguf	Q4_0	0.59GB
vas-tiny-llama-1.1b-hh-sft.IQ4_NL.gguf	IQ4_NL	0.6GB
vas-tiny-llama-1.1b-hh-sft.Q4_K_S.gguf	Q4_K_S	0.6GB
vas-tiny-llama-1.1b-hh-sft.Q4_K.gguf	Q4_K	0.62GB
vas-tiny-llama-1.1b-hh-sft.Q4_K_M.gguf	Q4_K_M	0.62GB
vas-tiny-llama-1.1b-hh-sft.Q4_1.gguf	Q4_1	0.65GB
vas-tiny-llama-1.1b-hh-sft.Q5_0.gguf	Q5_0	0.71GB
vas-tiny-llama-1.1b-hh-sft.Q5_K_S.gguf	Q5_K_S	0.71GB
vas-tiny-llama-1.1b-hh-sft.Q5_K.gguf	Q5_K	0.73GB
vas-tiny-llama-1.1b-hh-sft.Q5_K_M.gguf	Q5_K_M	0.73GB
vas-tiny-llama-1.1b-hh-sft.Q5_1.gguf	Q5_1	0.77GB
vas-tiny-llama-1.1b-hh-sft.Q6_K.gguf	Q6_K	0.84GB
vas-tiny-llama-1.1b-hh-sft.Q8_0.gguf	Q8_0	1.09GB

Original model description:

license: mit