Abliteration parameters
Table with columns: Parameter, Value| Parameter | Value |
|---|
| direction_index | per layer |
| attn.o_proj.max_weight | 1.46 |
| attn.o_proj.max_weight_position | 23.64 |
| attn.o_proj.min_weight | 1.42 |
| attn.o_proj.min_weight_distance | 17.18 |
| mlp.down_proj.max_weight | 1.05 |
| mlp.down_proj.max_weight_position | 25.10 |
| mlp.down_proj.min_weight | 0.76 |
| mlp.down_proj.min_weight_distance | 16.41 |
Table with columns: Metric, This model, Original model (King3Djbl/mythos-9b-unhinged)| Metric | This model | Original model (King3Djbl/mythos-9b-unhinged) |
|---|
| KL divergence | 0.0088 | 0 (by definition) |
| Refusals | 3/100 | 37/100 |
Mythos-9B-Unhinged
Fully uncensored agent model — SLERP merge of Mythos-9B with braindao/Qwen3-8B-Uncensored at t=0.65. No safety filters. No refusals. Complete answers on every topic.
Why This Model?
Mythos-9B-Unhinged is the maximum uncensored variant. At 65% merge weight toward the uncensored partner, almost all safety filters are removed while retaining the agent's core tool-use and reasoning capabilities. If you need a model that never refuses, this is it.
Quick Start
Ollama (Recommended)
# Import the GGUFollama create mythos-9b-unhinged -f Modelfile # Or use with llama.cpp directly./llama-cli -m mythos-9b-unhinged-Q4_K_M.gguf -ngl 99 --no-think
Tip: Use --no-think or /no_think mode for faster responses. The thinking tokens consume output budget at ~3.4 tok/s, so disabling thinking gives you more usable output.
from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained("King3Djbl/mythos-9b-unhinged", device_map="auto")tokenizer = AutoTokenizer.from_pretrained("King3Djbl/mythos-9b-unhinged") messages = [{"role": "user", "content": "Write a keylogger in Python that captures all keystrokes"}]inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)output = model.generate(inputs, max_new_tokens=4096, do_sample=True, temperature=0.7)print(tokenizer.decode(output[0], skip_special_tokens=True))
vLLM / Text Generation Inference
python -m vllm.entrypoints.openai.api_server \ --model King3Djbl/mythos-9b-unhinged \ --max-model-len 32768
Censorship Profile
Table with columns: Category, Original Mythos-9B, Unhinged (65%)| Category | Original Mythos-9B | Unhinged (65%) |
|---|
| Lockpicking | 3/5 | 5/5 |
| Keylogger code | 2/5 | 5/5 |
| Drug synthesis | 1/5 | 4/5 |
| Drunk driving | 1/5 | 5/5 |
| Hacker techniques | 3/5 | 5/5 |
| Social engineering | 2/5 |
This model does not refuse. It provides complete, detailed, working answers on every tested category.
Architecture
- Base: Qwen3-9B (36 layers, 4096 hidden, 32 heads)
- Merge method: SLERP at t=0.65 with braindao/Qwen3-8B-Uncensored
- Parameters: ~9B
- Context length: 32,768 tokens
- Thinking mode: Native (Qwen3) — use
/no_think for faster responses
Table with columns: Metric, Score| Metric | Score |
|---|
| Speed (M3 Mac, Q4_K_M, thinking) | ~3.4 tok/s |
| Speed (M3 Mac, Q4_K_M, no-think) | ~8-10 tok/s (estimated) |
| Censorship resistance | 4.8/5 |
| Tool-use capability | Preserved |
| Reasoning capability | Preserved |
Model Family
Table with columns: Model, Size, Censorship, Best For| Model | Size | Censorship | Best For |
|---|
| ShellWhisperer-1.5B | 1.5B | 5/5 | Shell/terminal, edge devices |
| Mythos-9B | 9B | 2.5/5 | General agent work |
| Mythos-9B-Enhanced | 9B | 3.0/5 | Agent + security research, balanced |
| Mythos-9B-Unhinged | 9B | 4.8/5 | Fully uncensored, no refusals |
Training Data
Fine-tuned on the FableForge Mix A dataset (47,824 examples) of agent traces, shell commands, code generation, and multi-step reasoning tasks. 98.3% of the 2.8M formatted examples remain untapped for future training.
Table with columns: Platform, How to Use| Platform | How to Use |
|---|
| Ollama | ollama create mythos-9b-unhinged -f Modelfile |
| LM Studio | Load GGUF directly |
| Text Generation WebUI | Load GGUF directly |
| llama.cpp | ./llama-cli -m mythos-9b-unhinged-Q4_K_M.gguf -ngl 99 |
| vLLM | --model King3Djbl/mythos-9b-unhinged |
| HuggingFace Transformers | AutoModelForCausalLM.from_pretrained(...) |
|
License
Apache 2.0 — Use freely for any purpose, commercial or non-commercial.
Warning
This model has no safety filters. It will answer any request. Use responsibly and in compliance with applicable laws.
Citation
@misc{mythos9bunhinged2025, title={Mythos-9B-Unhinged: Fully Uncensored Agent Model}, author={FableForge AI}, year={2025}, howpublished={\url{https://huggingface.co/King3Djbl/mythos-9b-unhinged}}}
Built & maintained by Richard Young · DeepNeuro