All credit goes to TheDrummer for the model: https://huggingface.co/TheDrummer/Behemoth-123B-v1.2 and Bartowski for the quants: https://huggingface.co/bartowski/Behemoth-123B-v1.2-GGUF I simply uploaded Q4_K_M quant here for my personal use, so I can download it through oobabooga WebUI on a rented instance. Ooba does not seem to be able to download GGUF files if they are placed in a separate folder, like Bartowski structures his quants on HF.