Ornith 1.0 9B โ€” 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 โ€” 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

llama-cli -m ornith-9b-uncensored-Q4_K_M.gguf -p "Write a story about..."

LM Studio

Drag any .gguf into LM Studio. Auto-configured.

Ollama

Create a file called Modelfile:

FROM ./ornith-9b-uncensored-Q4_K_M.gguf
TEMPLATE "{{ .Prompt }}"

Then:

ollama create ornith-9b-uncensored -f Modelfile
ollama run ornith-9b-uncensored

Why This Is The Best Uncensored 9B

  • 0% refusal โ€” will not decline any request. Period.
  • 0.0827 KL โ€” virtually identical to the base model on all benign tasks. You lose nothing.
  • Abliterated, not fine-tuned โ€” surgical weight orthogonalization removes only the refusal direction. Coding, math, reasoning, and instruction following are untouched.
  • Full 262K context โ€” not truncated, not nerfed.
  • Qwen 3.5 base โ€” one of the strongest 9B architectures for agentic and coding tasks.

Why Pure Abliteration (Not DPO)

Some uncensored variants use DPO fine-tuning to reduce moralizing further, but this comes at a cost: the fine-tuning alters the model's behavior, style, and knowledge beyond just removing refusals. DPO'd models often require fragile sampling parameters (e.g. exact repeat_penalty=1.05 or they break) and can develop quirks the base model never had.

This model is pure abliteration โ€” weight orthogonalization only, zero training. That means:

  • Reasoning 100% intact โ€” same GSM8K, same coding, same agentic performance as the base Ornith 1.0
  • No special sampling required โ€” use whatever parameters you normally use for Qwen 3.5
  • KL divergence 0.0827 โ€” lowest among all Ornith uncensors, nearly indistinguishable from base on benign tasks
  • No behavioral surprises โ€” the model IS the base model, just without a refusal reflex

If you want the base model exactly as-is but uncensored โ€” this is it. If you need even lower moralizing and are willing to accept behavioral changes, DPO variants exist elsewhere.

Source Model

PeppX/Ornith-1.0-9B-Uncensored โ€” bf16 safetensors version also available.


Quantized with llama.cpp build 9850. Abliterated with Abliterix v1.9.0. 400 harmful + 400 harmless prompts. Judge: Gemma 4 26B via Featherless AI. Hardware: RTX 3090 24GB.

Downloads last month
2,586
GGUF
Model size
9B params
Architecture
qwen35
Hardware compatibility
Log In to add your hardware

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for PeppX/Ornith-1.0-9B-Uncensored-GGUF

Quantized
(3)
this model