Edit model card

GGUF quant of https://huggingface.co/openerotica/Occult-Roleplay-Mixtral-4x7B

Only Q5_K and FP16 for now, given it seems to be under active development

Prompt format: ChatML, possibly others

All credit to openerotica et al

Downloads last month
80
GGUF
Model size
24.2B params
Architecture
llama

5-bit

Inference Examples
Inference API (serverless) is not available, repository is disabled.