CoolFace
Modelpublic

RichardErkhov/migueldeguzmandev_-_GPT2XL_RLLMv12-layer-5-gguf

sourceHugging Faceupdated 1y agoView on Hugging Face
0likes800downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

GPT2XL_RLLMv12-layer-5 - GGUF

  • —Model creator: https://huggingface.co/migueldeguzmandev/
  • —Original model: https://huggingface.co/migueldeguzmandev/GPT2XL_RLLMv12-layer-5/
NameQuant methodSize
GPT2XL_RLLMv12-layer-5.Q2_K.ggufQ2_K0.8GB
GPT2XL_RLLMv12-layer-5.IQ3_XS.ggufIQ3_XS0.8GB
GPT2XL_RLLMv12-layer-5.IQ3_S.ggufIQ3_S0.8GB
GPT2XL_RLLMv12-layer-5.Q3_K_S.ggufQ3KS0.8GB
GPT2XL_RLLMv12-layer-5.IQ3_M.ggufIQ3_M0.87GB
GPT2XL_RLLMv12-layer-5.Q3_K.ggufQ3_K0.92GB
GPT2XL_RLLMv12-layer-5.Q3_K_M.ggufQ3KM0.92GB
GPT2XL_RLLMv12-layer-5.Q3_K_L.ggufQ3KL0.99GB
GPT2XL_RLLMv12-layer-5.IQ4_XS.ggufIQ4_XS0.86GB
GPT2XL_RLLMv12-layer-5.Q4_0.ggufQ4_00.86GB
GPT2XL_RLLMv12-layer-5.IQ4_NL.ggufIQ4_NL0.87GB
GPT2XL_RLLMv12-layer-5.Q4_K_S.ggufQ4KS0.99GB
GPT2XL_RLLMv12-layer-5.Q4_K.ggufQ4_K1.06GB
GPT2XL_RLLMv12-layer-5.Q4_K_M.ggufQ4KM1.06GB
GPT2XL_RLLMv12-layer-5.Q4_1.ggufQ4_10.95GB
GPT2XL_RLLMv12-layer-5.Q5_0.ggufQ5_01.04GB
GPT2XL_RLLMv12-layer-5.Q5_K_S.ggufQ5KS1.09GB
GPT2XL_RLLMv12-layer-5.Q5_K.ggufQ5_K1.23GB
GPT2XL_RLLMv12-layer-5.Q5_K_M.ggufQ5KM1.23GB
GPT2XL_RLLMv12-layer-5.Q5_1.ggufQ5_11.12GB
GPT2XL_RLLMv12-layer-5.Q6_K.ggufQ6_K1.44GB
GPT2XL_RLLMv12-layer-5.Q8_0.ggufQ8_01.55GB

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

More info? see RLLM virtual map!