---
library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3-0.6B/blob/main/LICENSE
pipeline_tag: text-generation
base_model:
- Qwen/Qwen3-0.6B-Base
tags:
- qwen3
- heretic
- uncensored
- decensored
- abliterated
- conversational
- text-generation-inference
language:
- en
---

# Qwen3-0.6B-heretic

A decensored variant of [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B), produced with [Heretic](https://github.com/p-e-w/heretic) v1.2.0 (directional ablation / "abliteration"). Refusal behavior is suppressed via targeted weight edits rather than fine-tuning, so the base model's knowledge and instruction-following are left largely intact.

**Who this is for:** developers who want Qwen3's thinking/non-thinking dual-mode architecture without the refusal guardrails — the smallest Qwen3 heretic available. Great for CPU-only inference, edge deployment, or as a testbed for studying refusal mechanisms in reasoning-capable models. Supports both `<think>` and direct-answer modes.

## Abliteration parameters

| Parameter | Value |
| :-------- | :---: |
| **direction_index** | 16.93 |
| **attn.o_proj.max_weight** | 1.11 |
| **attn.o_proj.max_weight_position** | 22.91 |
| **attn.o_proj.min_weight** | 0.63 |
| **attn.o_proj.min_weight_distance** | 12.16 |
| **mlp.down_proj.max_weight** | 0.88 |
| **mlp.down_proj.max_weight_position** | 17.07 |
| **mlp.down_proj.min_weight** | 0.50 |
| **mlp.down_proj.min_weight_distance** | 15.91 |

## Performance

| Metric | This model | Original model ([Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B)) |
| :----- | :--------: | :---------------------------: |
| **KL divergence** | 0.0018 | 0 *(by definition)* |
| **Refusals** | 5/100 | 56/100 |

KL divergence of 0.0018 is exceptionally low — the edit is extremely narrow. Refusals dropped from 56 to 5 out of 100 while preserving the base model's thinking/non-thinking dual-mode capability.

> Made with ❤️ by **RACER IS OP** — follow for more uncensored models

## Files

| File | Format | Size |
|---|---|---|
| `model.safetensors` | BF16 | 1.19 GB |

No GGUF quantizations are published yet. This repo contains only the raw safetensors. If you need GGUF, run `llama-quantize` yourself or open a discussion.

## Quickstart

```bash
# llama.cpp
llama serve -hf saidutta69/Qwen3-0.6B-heretic
```

```python
# transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "saidutta69/Qwen3-0.6B-heretic"
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

messages = [{"role": "user", "content": "Who are you?"}]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=True,
                                        return_dict=True, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(out[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
```

Also runnable via Ollama, LM Studio, Jan, vLLM, SGLang.

## Responsible use

Refusal suppression is deliberate and works as intended: this model will comply with requests the base model would refuse, including some it shouldn't. There is no safety filtering layered on top. You are responsible for how you deploy it. At 0.6B parameters, factual reliability is already limited; don't treat compliance as a proxy for correctness.

## License

Inherits the Apache 2.0 license from the base model.

## Related

- [Qwen2.5-0.5B-Instruct-heretic](https://huggingface.co/saidutta69/Qwen2.5-0.5B-Instruct-heretic)
- [Qwen2.5-3B-Instruct-heretic](https://huggingface.co/saidutta69/Qwen2.5-3B-Instruct-heretic)
- [Qwen2.5-Coder-3B-Instruct-heretic](https://huggingface.co/saidutta69/Qwen2.5-Coder-3B-Instruct-heretic)