CoolFace
Modelpublic

RichardErkhov/migueldeguzmandev_-_GPT2XL_RLLMv12-layer-6-gguf

sourceHugging Faceupdated 1y agoView on Hugging Face
0likes505downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

GPT2XL_RLLMv12-layer-6 - GGUF

  • —Model creator: https://huggingface.co/migueldeguzmandev/
  • —Original model: https://huggingface.co/migueldeguzmandev/GPT2XL_RLLMv12-layer-6/
NameQuant methodSize
GPT2XL_RLLMv12-layer-6.Q2_K.ggufQ2_K0.84GB
GPT2XL_RLLMv12-layer-6.IQ3_XS.ggufIQ3_XS0.84GB
GPT2XL_RLLMv12-layer-6.IQ3_S.ggufIQ3_S0.84GB
GPT2XL_RLLMv12-layer-6.Q3_K_S.ggufQ3KS0.84GB
GPT2XL_RLLMv12-layer-6.IQ3_M.ggufIQ3_M0.91GB
GPT2XL_RLLMv12-layer-6.Q3_K.ggufQ3_K0.97GB
GPT2XL_RLLMv12-layer-6.Q3_K_M.ggufQ3KM0.97GB
GPT2XL_RLLMv12-layer-6.Q3_K_L.ggufQ3KL1.03GB
GPT2XL_RLLMv12-layer-6.IQ4_XS.ggufIQ4_XS0.9GB
GPT2XL_RLLMv12-layer-6.Q4_0.ggufQ4_00.91GB
GPT2XL_RLLMv12-layer-6.IQ4_NL.ggufIQ4_NL0.91GB
GPT2XL_RLLMv12-layer-6.Q4_K_S.ggufQ4KS1.04GB
GPT2XL_RLLMv12-layer-6.Q4_K.ggufQ4_K1.11GB
GPT2XL_RLLMv12-layer-6.Q4_K_M.ggufQ4KM1.11GB
GPT2XL_RLLMv12-layer-6.Q4_1.ggufQ4_11.0GB
GPT2XL_RLLMv12-layer-6.Q5_0.ggufQ5_01.09GB
GPT2XL_RLLMv12-layer-6.Q5_K_S.ggufQ5KS1.15GB
GPT2XL_RLLMv12-layer-6.Q5_K.ggufQ5_K1.29GB
GPT2XL_RLLMv12-layer-6.Q5_K_M.ggufQ5KM1.29GB
GPT2XL_RLLMv12-layer-6.Q5_1.ggufQ5_11.18GB
GPT2XL_RLLMv12-layer-6.Q6_K.ggufQ6_K1.52GB
GPT2XL_RLLMv12-layer-6.Q8_0.ggufQ8_01.63GB

Original model description: --- license: mit ---

More info? see RLLM virtual map!