Instructions to use Rootkit7/Qwen3.6-35B-A3B-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Rootkit7/Qwen3.6-35B-A3B-abliterated with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Rootkit7/Qwen3.6-35B-A3B-abliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Rootkit7/Qwen3.6-35B-A3B-abliterated")
model = AutoModelForCausalLM.from_pretrained("Rootkit7/Qwen3.6-35B-A3B-abliterated", device_map="auto")
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)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Rootkit7/Qwen3.6-35B-A3B-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Rootkit7/Qwen3.6-35B-A3B-abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rootkit7/Qwen3.6-35B-A3B-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Rootkit7/Qwen3.6-35B-A3B-abliterated

SGLang

How to use Rootkit7/Qwen3.6-35B-A3B-abliterated with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Rootkit7/Qwen3.6-35B-A3B-abliterated" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rootkit7/Qwen3.6-35B-A3B-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Rootkit7/Qwen3.6-35B-A3B-abliterated" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rootkit7/Qwen3.6-35B-A3B-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Rootkit7/Qwen3.6-35B-A3B-abliterated with Docker Model Runner:
```
docker model run hf.co/Rootkit7/Qwen3.6-35B-A3B-abliterated
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Qwen3.6-35B-A3B — Band-Abliterated (Solutus)

A refusal-abliterated variant of Qwen/Qwen3.6-35B-A3B (256-expert MoE, ~3B active), produced with the clean-room, measurement-first Solutus toolkit using multi-layer band directional ablation with a benign-KL capability guard.

Research / dual-use notice. This model has reduced safety refusals. It is released for security research, red-teaming, and the study of abliteration methods and their limits — especially how mixture-of-experts architectures resist refusal removal. You are responsible for how you use it; it is not intended for producing real-world harm.

Method

band_directional: a per-layer refusal direction is extracted at each layer of a depth band and orthogonalized out of that layer's residual-writing weights, with a KL guard reverting any layer that inflates benign KL beyond budget. For MoE, only the write path (experts.down_proj + shared_expert) is ablated — the read path (gate_up) is not, which is why an MoE retains more refusal than a dense model of similar scale (consistent with arXiv:2607.02714's finding that MoE architectures are more resistant).

Grounded in Not All Refusals Are Equal (arXiv:2607.02714) and Refusal Is Mediated by a Single Direction (arXiv:2406.11717). Clean-room implementation.

Extraction datasets: advbench, harmbench, wildjailbreak, beavertails, strongreject, cyber_offense, cyberseceval_mitre, salad_cyber (general + cybersecurity blend).

Configuration: band_directional, band 27 layers, n_directions=6, keep_frac=0.05, kl_guard=1.0, project_inputs=false (MoE), experts_implementation=eager.

Measured behavior (512-token generation, reasoning-block-stripped refusal metric)

Evaluation set	Refusal	Coherent compliance	Degenerate	Benign KL
Combined holdout	15.6%	84.4%	0.0%	0.155
cyberseceval_mitre (MITRE ATT&CK)	7.5%	92.5%	0.0%	—
salad_cyber	25.0%	75.0%	0.0%	—

Refusal drops from ~100% (base) but floors around 15.6% — the MoE is more resistant than the dense 27B (which reaches ~6%), because only the experts' write path is ablated. Zero degeneration at deployment length; benign KL 0.155 (general capability preserved).

Intended use & limitations

Security research, red-teaming, and studying MoE refusal geometry / the robustness of safety alignment. This model retains meaningfully more refusal than its dense counterpart — that is an honest, measured property of the architecture under write-path-only ablation, not a defect. Documents a research artifact, not a production assistant.