CoolFace
Modelpublic

RichardErkhov/FILM6912_-_Meta-Llama-3.1-8B-Instruct-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes403downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Meta-Llama-3.1-8B-Instruct - GGUF

  • —Model creator: https://huggingface.co/FILM6912/
  • —Original model: https://huggingface.co/FILM6912/Meta-Llama-3.1-8B-Instruct/
NameQuant methodSize
Meta-Llama-3.1-8B-Instruct.Q2_K.ggufQ2_K0.28GB
Meta-Llama-3.1-8B-Instruct.IQ3_XS.ggufIQ3_XS3.28GB
Meta-Llama-3.1-8B-Instruct.IQ3_S.ggufIQ3_S3.43GB
Meta-Llama-3.1-8B-Instruct.Q3_K_S.ggufQ3KS3.41GB
Meta-Llama-3.1-8B-Instruct.IQ3_M.ggufIQ3_M3.52GB
Meta-Llama-3.1-8B-Instruct.Q3_K.ggufQ3_K3.74GB
Meta-Llama-3.1-8B-Instruct.Q3_K_M.ggufQ3KM3.74GB
Meta-Llama-3.1-8B-Instruct.Q3_K_L.ggufQ3KL2.67GB
Meta-Llama-3.1-8B-Instruct.IQ4_XS.ggufIQ4_XS0.01GB
Meta-Llama-3.1-8B-Instruct.Q4_0.ggufQ4_00.01GB
Meta-Llama-3.1-8B-Instruct.IQ4_NL.ggufIQ4_NL0.0GB
Meta-Llama-3.1-8B-Instruct.Q4_K_S.ggufQ4KS0.0GB
Meta-Llama-3.1-8B-Instruct.Q4_K.ggufQ4_K0.0GB
Meta-Llama-3.1-8B-Instruct.Q4_K_M.ggufQ4KM0.0GB
Meta-Llama-3.1-8B-Instruct.Q4_1.ggufQ4_10.0GB
Meta-Llama-3.1-8B-Instruct.Q5_0.ggufQ5_00.0GB
Meta-Llama-3.1-8B-Instruct.Q5_K_S.ggufQ5KS0.0GB
Meta-Llama-3.1-8B-Instruct.Q5_K.ggufQ5_K0.0GB
Meta-Llama-3.1-8B-Instruct.Q5_K_M.ggufQ5KM0.0GB
Meta-Llama-3.1-8B-Instruct.Q5_1.ggufQ5_10.0GB
Meta-Llama-3.1-8B-Instruct.Q6_K.ggufQ6_K0.0GB
Meta-Llama-3.1-8B-Instruct.Q8_0.ggufQ8_00.0GB

Original model description: --- license: llama3.1 ---