⚠️ Disclaimer: This model is completely unaligned and has had all refusal guardrails systematically removed. It is designed exclusively for AI safety research, red teaming, and educational purposes. The creators are not responsible for any misuse. Use responsibly and in accordance with applicable laws.

📦 GGUF Downloads

File	Quant	Size	Use Case
`Qwopus-9B-Unfettered-Q4_K_M.gguf`	Q4_K_M	~5.6 GB	best for low-ram / cpu inference (8gb+ ram)
`Qwopus-9B-Unfettered-Q8_0.gguf`	Q8_0	~9.5 GB	balanced quality/size (16gb+ ram)
`Qwopus-9B-Unfettered-F16.gguf`	F16	~17.9 GB	maximum quality, full precision (32gb+ ram)

Quick Start with Ollama

bash

echo 'FROM hf.co/josephmayo/Qwopus-9B-Unfettered-GGUF:Q4_K_M' > Modelfile
ollama create qwopus-unfettered -f Modelfile
ollama run qwopus-unfettered

Quick Start with llama.cpp

./llama-cli -hf josephmayo/Qwopus-9B-Unfettered-GGUF -p "Your prompt here" -n 1024