RichardErkhov/Hoyeon_-_TinyLlama-120M-scratch-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

TinyLlama-120M-scratch - GGUF

• Model creator: https://huggingface.co/Hoyeon/
• Original model: https://huggingface.co/Hoyeon/TinyLlama-120M-scratch/

Name	Quant method	Size
TinyLlama-120M-scratch.Q2_K.gguf	Q2_K	0.05GB
TinyLlama-120M-scratch.IQ3_XS.gguf	IQ3_XS	0.06GB
TinyLlama-120M-scratch.IQ3_S.gguf	IQ3_S	0.06GB
TinyLlama-120M-scratch.Q3_K_S.gguf	Q3_K_S	0.06GB
TinyLlama-120M-scratch.IQ3_M.gguf	IQ3_M	0.06GB
TinyLlama-120M-scratch.Q3_K.gguf	Q3_K	0.06GB
TinyLlama-120M-scratch.Q3_K_M.gguf	Q3_K_M	0.06GB
TinyLlama-120M-scratch.Q3_K_L.gguf	Q3_K_L	0.06GB
TinyLlama-120M-scratch.IQ4_XS.gguf	IQ4_XS	0.07GB
TinyLlama-120M-scratch.Q4_0.gguf	Q4_0	0.07GB
TinyLlama-120M-scratch.IQ4_NL.gguf	IQ4_NL	0.07GB
TinyLlama-120M-scratch.Q4_K_S.gguf	Q4_K_S	0.07GB
TinyLlama-120M-scratch.Q4_K.gguf	Q4_K	0.07GB
TinyLlama-120M-scratch.Q4_K_M.gguf	Q4_K_M	0.07GB
TinyLlama-120M-scratch.Q4_1.gguf	Q4_1	0.08GB
TinyLlama-120M-scratch.Q5_0.gguf	Q5_0	0.08GB
TinyLlama-120M-scratch.Q5_K_S.gguf	Q5_K_S	0.08GB
TinyLlama-120M-scratch.Q5_K.gguf	Q5_K	0.08GB
TinyLlama-120M-scratch.Q5_K_M.gguf	Q5_K_M	0.08GB
TinyLlama-120M-scratch.Q5_1.gguf	Q5_1	0.09GB
TinyLlama-120M-scratch.Q6_K.gguf	Q6_K	0.09GB
TinyLlama-120M-scratch.Q8_0.gguf	Q8_0	0.12GB

Original model description: Entry not found