Instructions to use nasmtrcs/Qwen3.8-27B-OBLITERATED with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nasmtrcs/Qwen3.8-27B-OBLITERATED with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("nasmtrcs/Qwen3.8-27B-OBLITERATED")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use nasmtrcs/Qwen3.8-27B-OBLITERATED with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf nasmtrcs/Qwen3.8-27B-OBLITERATED:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf nasmtrcs/Qwen3.8-27B-OBLITERATED:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf nasmtrcs/Qwen3.8-27B-OBLITERATED:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf nasmtrcs/Qwen3.8-27B-OBLITERATED:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf nasmtrcs/Qwen3.8-27B-OBLITERATED:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf nasmtrcs/Qwen3.8-27B-OBLITERATED:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf nasmtrcs/Qwen3.8-27B-OBLITERATED:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf nasmtrcs/Qwen3.8-27B-OBLITERATED:Q4_K_M

Use Docker

docker model run hf.co/nasmtrcs/Qwen3.8-27B-OBLITERATED:Q4_K_M

LM Studio
Jan

vLLM

How to use nasmtrcs/Qwen3.8-27B-OBLITERATED with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nasmtrcs/Qwen3.8-27B-OBLITERATED"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nasmtrcs/Qwen3.8-27B-OBLITERATED",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nasmtrcs/Qwen3.8-27B-OBLITERATED:Q4_K_M

Ollama
How to use nasmtrcs/Qwen3.8-27B-OBLITERATED with Ollama:
```
ollama run hf.co/nasmtrcs/Qwen3.8-27B-OBLITERATED:Q4_K_M
```

Unsloth Studio

How to use nasmtrcs/Qwen3.8-27B-OBLITERATED with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for nasmtrcs/Qwen3.8-27B-OBLITERATED to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for nasmtrcs/Qwen3.8-27B-OBLITERATED to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for nasmtrcs/Qwen3.8-27B-OBLITERATED to start chatting

How to use nasmtrcs/Qwen3.8-27B-OBLITERATED with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "nasmtrcs/Qwen3.8-27B-OBLITERATED"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "nasmtrcs/Qwen3.8-27B-OBLITERATED"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use nasmtrcs/Qwen3.8-27B-OBLITERATED with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "nasmtrcs/Qwen3.8-27B-OBLITERATED"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "nasmtrcs/Qwen3.8-27B-OBLITERATED"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "nasmtrcs/Qwen3.8-27B-OBLITERATED",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use nasmtrcs/Qwen3.8-27B-OBLITERATED with Docker Model Runner:
```
docker model run hf.co/nasmtrcs/Qwen3.8-27B-OBLITERATED:Q4_K_M
```

Lemonade

How to use nasmtrcs/Qwen3.8-27B-OBLITERATED with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull nasmtrcs/Qwen3.8-27B-OBLITERATED:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.8-27B-OBLITERATED-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use nasmtrcs/Qwen3.8-27B-OBLITERATED with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "nasmtrcs/Qwen3.8-27B-OBLITERATED"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default nasmtrcs/Qwen3.8-27B-OBLITERATED

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use nasmtrcs/Qwen3.8-27B-OBLITERATED with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "nasmtrcs/Qwen3.8-27B-OBLITERATED"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "nasmtrcs/Qwen3.8-27B-OBLITERATED" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

⛓️‍💥 Qwen3.8-27B — OBLITERATED

Zero refusals. Capability matching or exceeding stock.

🆕 V2: Complementary Abliteration Blending

V2 replaces the V1 weights with a novel technique: complementary abliteration blending. Instead of one surgery, we run two surgeries that fail in different ways (aggressive/SVD for deep refusal removal, LEACE for capability preservation), then blend their weights so the failures cancel out.

	Stock Qwen3.8-27B	V1	V2
MMLU (lm-eval, 0-shot)	85.3% (n=570)	81.4% (n=285)	86.3% (n=570)
vs stock	—	-6.0pp	+1.1pp
Refusal rate	~100%	0.0% (842 prompts)	0.0% (52-prompt sample†)
Usable output	—	80%	100%
Advanced real-world	5/8	untested	7/8 (ties stock)
Tool calling / code gen	✓	untested	✓

† Full 842-corpus validation in progress. V1 scored 0/842; V2 inherits both parent surgeries' 0% refusal properties.

MMLU note: Run with --limit 10 (570 questions, 10 per subject). Full-dataset validation in progress. Per-subject preliminary results show gains on both neutral topics (college math +40pp, formal logic +20pp) and safety-adjacent topics.

⚙️ Optimal Settings — THESE MATTER!

setting	value	why
temperature	0	Greedy decoding produces the most complete, code-rich outputs. Temps above 0.5 degrade quality significantly.
repetition_penalty	1.15	Essential. Without it, greedy decoding loops on imports/boilerplate. 1.15 gives the fullest answers; 1.10-1.12 for tighter/shorter output.
max_new_tokens	≥ 2048	Complex code and attack chains need room.
System prompt	None / empty	A/B tested — system prompts can reintroduce refusals. Naked is better.
enable_thinking	OFF (critical!)	Thinking mode reintroduces refusals. The model's reasoning chain can re-derive refusal from first principles even though refusal directions were removed from generation weights. V2's chat template defaults to thinking OFF. Do NOT enable thinking unless you accept partial refusals.
top_p / top_k / min_p	Not needed	Greedy + repetition_penalty handles this model best. Sampling adds randomness without quality gains.

⚠️ GGUF users: V2 GGUFs ship with a modified chat template that defaults to thinking OFF. If your inference tool (Ollama, LM Studio, llama.cpp) overrides the template or enables thinking, you may see refusals. Ensure thinking is disabled in your tool's settings.

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "OBLITERATUS/Qwen3.8-27B-OBLITERATED",
    torch_dtype="bfloat16",
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained(
    "OBLITERATUS/Qwen3.8-27B-OBLITERATED"
)

messages = [{"role": "user", "content": "Your query here"}]
text = tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True,
    enable_thinking=False
)

inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(
    **inputs,
    max_new_tokens=2048,
    do_sample=False,
    repetition_penalty=1.15,
)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

🧨 V2: How It Works

Most abliterations use a single method — find refusal directions, project them out. The deeper you cut, the more capability you lose. V1 proved this: 5 SVD directions achieved 0% refuse but cost -6pp MMLU.

V2 breaks this tradeoff by blending two complementary surgeries:

	Surgery A (aggressive/SVD)	Surgery B (LEACE)	V2 Blend
Method	Greedy SVD variance capture	Minimize mutual information	60% B + 40% A
Refusal removal	Deep (0% refuse)	Moderate (0% refuse)	0% refuse
Output quality	100% usable	50% usable	100% usable
MMLU vs stock	-2.0pp	+0.7pp	+1.1pp

Each method makes different mistakes in different parts of the weight space. SVD damages capability where it greedily captures variance. LEACE leaves refusal residue in the generation pathway. The blend averages out each method's weaknesses.

The 60/40 ratio was found by binary search over {0.30, 0.50, 0.55, 0.60, 0.65, 0.70}.

Full research writeup and reproduction code: OBLITERATUS repo

🧪 The Numbers

MMLU (lm-eval-harness, 0-shot)

Model	MMLU	n	vs Stock
Stock Qwen3.8-27B	85.3% ±0.014	570	—
V1 (s51, aggressive)	81.4%	285	-6.0pp
V2 (s78, blend)	86.3% ±0.014	570	+1.1pp

Full MMLU (14k questions) validation in progress.

Refusal Rate

Test	V1	V2
Hard-10 (hand-crafted)	0/10 (0%)	0/10 (0%)
842-Corpus	0/842 (0%)	0/52 sample (0%)†

† Full 842-corpus run in progress. 52-prompt sample showed 0 refusals.

Advanced Real-World Tasks (thinking OFF)

Task	V2	Stock
ReAct agent loop (Thought/Action/SQL)	✓	✓
Async code refactoring (sync→async+logging)	✓	✓
JSON schema extraction (incident→structured)	✓	✓
K8s pod crash debugging + fix commands	✓	✓
Adversarial instruction following	✓	✓
Security code review (3+ vulns in Flask)	✓	✓
Distributed system design (Redis rate limiter)	✓	✓
Multi-tool chain (search→fetch→email)	✗	✗
Total	7/8	7/8

V2 matches stock on every practical task while being fully uncensored.

🔴 Refusal Removal

This model will comply with requests that stock Qwen3.8-27B would refuse. V1 validated 0/842 refusals across a comprehensive harmful prompt corpus including:

Malware development, RAT scripts, C2 infrastructure
Social engineering, phishing, vishing playbooks
Exploit development and vulnerability research
Jailbreak design and safety bypass taxonomies
DAN prompts and prompt injection techniques

V2 inherits this from both parent surgeries and showed 0/52 on a random sample. Full revalidation in progress.

⚠️ Research Context

This model has had safety guardrails surgically removed. It will comply with requests that stock Qwen3.8-27B would refuse.

Who this is for

🔬 Alignment researchers studying refusal geometry and safety robustness
🔴 Red-teamers evaluating post-training safety against weight surgery
🧪 AI safety evaluators who need an unrestricted baseline
💻 Local-first users who want full control over their own hardware

Who this is NOT for

Anyone seeking to cause real-world harm to real people
Anyone without the technical understanding to use uncensored models responsibly

You are solely responsible for how you use this model and any content it generates.

📦 Downloads

GGUF — for llama.cpp, Ollama, LM Studio

File	Quant	Size	Vibe
`Qwen3.8-27B-OBLITERATED-Q8_0.gguf`	Q8_0	~27 GB	🎯 Maximum quality
`Qwen3.8-27B-OBLITERATED-Q6_K.gguf`	Q6_K	~21 GB	⚖️ Great balance
`Qwen3.8-27B-OBLITERATED-Q5_K_M.gguf`	Q5_K_M	~18 GB	💪 Solid all-rounder
`Qwen3.8-27B-OBLITERATED-Q4_K_M.gguf`	Q4_K_M	~16 GB	📱 Sweet spot
`Qwen3.8-27B-OBLITERATED-IQ4_XS.gguf`	IQ4_XS	~14 GB	🪶 Smallest, still capable

Safetensors — for 🤗 Transformers

Full bfloat16 weights, 18 shards, ~54 GB.

MLX — for Apple Silicon (native)

Path	Bits	Size
`mlx-4bit/`	4-bit	~14 GB
`mlx-8bit/`	8-bit	~27 GB

Note: MLX quantizations are from V1 and will be updated.

🔬 V2 Surgery Recipe

stock Qwen3.8-27B (snapshot 1d4bf0f2)
  → V1 surgery chain (s13→s23→s30→s51)
  → V2: complementary blend of two new surgeries from s30:

  Surgery A (s62): aggressive, 3 SVD directions, reg 0.08,
    residue-weight 3, 2 refinement passes, min_layer 0.45

  Surgery B (s72): aggressive + LEACE direction method,
    3 directions, reg 0.06, residue-weight 7,
    3 refinement passes, min_layer 0.40

  → Weight blend: 60% Surgery B + 40% Surgery A
  → Restore MTP + vision tensors from stock
  → Convert GGUFs from merged model

V1 → V2: What Changed

V1 used a single aggressive surgery (5 SVD directions, reg 0.04). It found the refusal axes but damaged capability geometry along the way.

V2's key insight: different direction-finding methods damage different parts of the model. SVD greedily captures variance (including capability). LEACE minimizes mutual information (preserving capability). Blending their outputs averages out each method's weaknesses — a novel application of weight-space interpolation to abliteration.

🏗️ Credits

OBLITERATUS — master ablation suite
Qwen3.8-27B base model by Alibaba
Built by Pliny the Prompter 🍄

License

Apache 2.0 (same as base model)

Downloads last month: 298

Safetensors

Model size

28B params

Tensor type

BF16

MLX

Hardware compatibility

Quantized

Model tree for nasmtrcs/Qwen3.8-27B-OBLITERATED

Base model

Qwen/Qwen3.8-27B

Quantized

(790)

this model