CoolFace
Modelpublic

RichardErkhov/TaylorAI_-_Flash-Llama-13B-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes210downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Flash-Llama-13B - GGUF

  • —Model creator: https://huggingface.co/TaylorAI/
  • —Original model: https://huggingface.co/TaylorAI/Flash-Llama-13B/
NameQuant methodSize
Flash-Llama-13B.Q2_K.ggufQ2_K4.52GB
Flash-Llama-13B.IQ3_XS.ggufIQ3_XS4.99GB
Flash-Llama-13B.IQ3_S.ggufIQ3_S5.27GB
Flash-Llama-13B.Q3_K_S.ggufQ3KS5.27GB
Flash-Llama-13B.IQ3_M.ggufIQ3_M5.57GB
Flash-Llama-13B.Q3_K.ggufQ3_K5.9GB
Flash-Llama-13B.Q3_K_M.ggufQ3KM5.9GB
Flash-Llama-13B.Q3_K_L.ggufQ3KL6.45GB
Flash-Llama-13B.IQ4_XS.ggufIQ4_XS6.54GB
Flash-Llama-13B.Q4_0.ggufQ4_06.86GB
Flash-Llama-13B.IQ4_NL.ggufIQ4_NL6.9GB
Flash-Llama-13B.Q4_K_S.ggufQ4KS6.91GB
Flash-Llama-13B.Q4_K.ggufQ4_K7.33GB
Flash-Llama-13B.Q4_K_M.ggufQ4KM7.33GB
Flash-Llama-13B.Q4_1.ggufQ4_17.61GB
Flash-Llama-13B.Q5_0.ggufQ5_08.36GB
Flash-Llama-13B.Q5_K_S.ggufQ5KS8.36GB
Flash-Llama-13B.Q5_K.ggufQ5_K8.6GB
Flash-Llama-13B.Q5_K_M.ggufQ5KM8.6GB
Flash-Llama-13B.Q5_1.ggufQ5_19.1GB
Flash-Llama-13B.Q6_K.ggufQ6_K9.95GB
Flash-Llama-13B.Q8_0.ggufQ8_012.88GB

Original model description: Entry not found