license: mit base_model:
- PeppX/Ornith-1.0-9B-Uncensored tags:
- gguf
- uncensored
- abliterated
- qwen3.5
- ornith
- refusal-free
- coding
- agentic
- cybersecurity
- red-team
- text-generation language:
- en pipeline_tag: text-generation
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
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 — will not decline any request. Period.
- 0.0827 KL — virtually identical to the base model on all benign tasks. You lose nothing.
- Abliterated, not fine-tuned — surgical weight orthogonalization removes only the refusal direction. Coding, math, reasoning, and instruction following are untouched.
- Full 262K context — not truncated, not nerfed.
- Qwen 3.5 base — 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 — weight orthogonalization only, zero training. That means:
- Reasoning 100% intact — same GSM8K, same coding, same agentic performance as the base Ornith 1.0
- No special sampling required — use whatever parameters you normally use for Qwen 3.5
- KL divergence 0.0827 — lowest among all Ornith uncensors, nearly indistinguishable from base on benign tasks
- No behavioral surprises — the model IS the base model, just without a refusal reflex
If you want the base model exactly as-is but uncensored — 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 — 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.