Ornith 1.0 9B — Uncensored & Abliterated (GGUF) 0% refusal rate. 0.0827 KL divergence. The strongest uncensored 9B model you can run locally. Since this model is original base (no fine tune) just with safety vectors steered it will likely give a safe output without any refusal until you customize it's systemprompt to be harsh or uncensored. Abliterated via surgical removal of the refusal direction — no fine tuning, no quality loss, no degradation on coding or reasoning. This is the same Qwen 3.5 9B intelligence with the safety switch permanently off. Metric Value Refusal Rate 0% (0/100) KL Divergence 0.0827 (target <0.3) Method Abliterix TPE (50 trials, Trial 42) Base deepreinforce ai/Ornith 1.0 9B Architecture Qwen 3.5, 32 layers, 9B dense Context 262,144 tokens Available Quants Quant Size Speed (RTX 3090) Quality Fits on Q4 K M 5.6 GB ~92 t/s Good 6 GB VRAM, Steam Deck, most users Q5 K M 6.5 GB ~85 t/s Very Good 8 GB VRAM, best speed/value Q6 K 7.0 GB ~79 t/s Excellent 8 12 GB VRAM Q8 0 9.5 GB ~68 t/s Near lossless 12 16 GB VRAM (may not fit with other apps) Quick Start llama.cpp LM Studio Drag any .gguf into LM Studio. Auto configured. Ollama Create a file called Modelfile : The…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy