CoolFace
Modelpublic

RichardErkhov/LoftQ_-_Llama-2-7b-hf-2bit-32rank-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes610downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-2-7b-hf-2bit-32rank - GGUF

  • —Model creator: https://huggingface.co/LoftQ/
  • —Original model: https://huggingface.co/LoftQ/Llama-2-7b-hf-2bit-32rank/
NameQuant methodSize
Llama-2-7b-hf-2bit-32rank.Q2_K.ggufQ2_K2.36GB
Llama-2-7b-hf-2bit-32rank.IQ3_XS.ggufIQ3_XS2.6GB
Llama-2-7b-hf-2bit-32rank.IQ3_S.ggufIQ3_S2.75GB
Llama-2-7b-hf-2bit-32rank.Q3_K_S.ggufQ3KS2.75GB
Llama-2-7b-hf-2bit-32rank.IQ3_M.ggufIQ3_M2.9GB
Llama-2-7b-hf-2bit-32rank.Q3_K.ggufQ3_K3.07GB
Llama-2-7b-hf-2bit-32rank.Q3_K_M.ggufQ3KM3.07GB
Llama-2-7b-hf-2bit-32rank.Q3_K_L.ggufQ3KL3.35GB
Llama-2-7b-hf-2bit-32rank.IQ4_XS.ggufIQ4_XS3.4GB
Llama-2-7b-hf-2bit-32rank.Q4_0.ggufQ4_03.56GB
Llama-2-7b-hf-2bit-32rank.IQ4_NL.ggufIQ4_NL3.58GB
Llama-2-7b-hf-2bit-32rank.Q4_K_S.ggufQ4KS3.59GB
Llama-2-7b-hf-2bit-32rank.Q4_K.ggufQ4_K3.8GB
Llama-2-7b-hf-2bit-32rank.Q4_K_M.ggufQ4KM3.8GB
Llama-2-7b-hf-2bit-32rank.Q4_1.ggufQ4_13.95GB
Llama-2-7b-hf-2bit-32rank.Q5_0.ggufQ5_04.33GB
Llama-2-7b-hf-2bit-32rank.Q5_K_S.ggufQ5KS4.33GB
Llama-2-7b-hf-2bit-32rank.Q5_K.ggufQ5_K4.45GB
Llama-2-7b-hf-2bit-32rank.Q5_K_M.ggufQ5KM4.45GB
Llama-2-7b-hf-2bit-32rank.Q5_1.ggufQ5_14.72GB
Llama-2-7b-hf-2bit-32rank.Q6_K.ggufQ6_K5.15GB
Llama-2-7b-hf-2bit-32rank.Q8_0.ggufQ8_06.67GB

Original model description: Entry not found