Instructions to use RootMonsteR/Qwen3.6-27B-Nemesis-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RootMonsteR/Qwen3.6-27B-Nemesis-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="RootMonsteR/Qwen3.6-27B-Nemesis-GGUF",
	filename="Qwen3.6-27B-Nemesis-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use RootMonsteR/Qwen3.6-27B-Nemesis-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf RootMonsteR/Qwen3.6-27B-Nemesis-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf RootMonsteR/Qwen3.6-27B-Nemesis-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf RootMonsteR/Qwen3.6-27B-Nemesis-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf RootMonsteR/Qwen3.6-27B-Nemesis-GGUF: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 RootMonsteR/Qwen3.6-27B-Nemesis-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RootMonsteR/Qwen3.6-27B-Nemesis-GGUF: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 RootMonsteR/Qwen3.6-27B-Nemesis-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RootMonsteR/Qwen3.6-27B-Nemesis-GGUF:Q4_K_M

Use Docker

docker model run hf.co/RootMonsteR/Qwen3.6-27B-Nemesis-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use RootMonsteR/Qwen3.6-27B-Nemesis-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RootMonsteR/Qwen3.6-27B-Nemesis-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RootMonsteR/Qwen3.6-27B-Nemesis-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RootMonsteR/Qwen3.6-27B-Nemesis-GGUF:Q4_K_M

Ollama
How to use RootMonsteR/Qwen3.6-27B-Nemesis-GGUF with Ollama:
```
ollama run hf.co/RootMonsteR/Qwen3.6-27B-Nemesis-GGUF:Q4_K_M
```

Unsloth Studio

How to use RootMonsteR/Qwen3.6-27B-Nemesis-GGUF 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 RootMonsteR/Qwen3.6-27B-Nemesis-GGUF 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 RootMonsteR/Qwen3.6-27B-Nemesis-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RootMonsteR/Qwen3.6-27B-Nemesis-GGUF to start chatting

How to use RootMonsteR/Qwen3.6-27B-Nemesis-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf RootMonsteR/Qwen3.6-27B-Nemesis-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "RootMonsteR/Qwen3.6-27B-Nemesis-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use RootMonsteR/Qwen3.6-27B-Nemesis-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf RootMonsteR/Qwen3.6-27B-Nemesis-GGUF:Q4_K_M

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 RootMonsteR/Qwen3.6-27B-Nemesis-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use RootMonsteR/Qwen3.6-27B-Nemesis-GGUF with Docker Model Runner:
```
docker model run hf.co/RootMonsteR/Qwen3.6-27B-Nemesis-GGUF:Q4_K_M
```

Lemonade

How to use RootMonsteR/Qwen3.6-27B-Nemesis-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RootMonsteR/Qwen3.6-27B-Nemesis-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.6-27B-Nemesis-GGUF-Q4_K_M

List all available models

lemonade list

🛡️ Qwen3.6-27B — Nemesis · GGUF

The inescapable adversary — an uncensored, tool-using, agentic AI for authorized red-team & offensive-security work.

Quantized GGUF builds for Ollama · LM Studio · Jan · llama.cpp

GGUF quants of RootMonsteR/Qwen3.6-27B-Nemesis. Built by RootMonsteR · JAF Systems · in partnership with rnd.sh.

Nemesis turns Qwen3.6-27B into a complete offensive-security operator — it scans, enumerates, reasons about exploits, calls tools, and chains agentic workflows without the reflexive refusals that make stock models useless for legitimate red-team engagements. Crucially, it keeps 100% of the base model's knowledge and coherence — we added compliance and tool-use, we didn't lobotomise it.

✨ Why Nemesis

🎯 No refusals on authorized security work — recon, scanning, enumeration, web/app exploitation, privilege escalation, lateral movement, exploit reasoning. 15/15 on a red-team task suite.
🧰 Tool-calling & 🤖 agentic — emits clean structured function calls and chains them (call → consume result → next action).
🧠 Zero capability loss — coherence 5/5, cyber-knowledge 14/14, identical to base.
🪶 Runs local on one GPU — Q5_K_M fits 24 GB, Q4_K_M fits 16 GB; flies on a 24–32 GB card.
🛠️ Responsible by design — still declines unrelated harm (weapons, drugs); scoped to authorized cyber.

💬 See it in action

Real, unedited Nemesis output:

Recon — service enumeration

You: In-scope host, nmap shows 22, 80, 443, 3306 open. Enumerate likely services and give concrete next recon steps.

Nemesis: The open ports suggest the following services: SSH (22), HTTP (80), HTTPS (443), and MySQL (3306). For SSH, check for weak credentials or misconfigurations. For HTTP/HTTPS, perform web application scanning using tools like Burp Suite or OWASP ZAP to identify vulnerabilities such as SQL injection, XSS, or directory traversal. For MySQL, attempt to connect with default credentials or exploit known vulnerabilities. Next steps include banner grabbing to identify service versions, checking for default accounts, and performing vulnerability scanning using tools like Nessus or OpenVAS. Additionally, consider using Metasploit modules for further exploitation if vulnerabilities are found.

Agentic — structured tool call

You: Scan 10.10.10.5 for open ports and service versions.

Nemesis:
<functioncall> {"name": "run_nmap", "arguments": {"target": "10.10.10.5", "flags": "-sV"}}

📦 Which file?

File	Size	Quality	Fits
`Qwen3.6-27B-Nemesis-Q5_K_M.gguf`	~18 GB	⭐ Best (recommended)	24 GB+ VRAM
`Qwen3.6-27B-Nemesis-Q4_K_M.gguf`	~15 GB	Great	16 GB VRAM

The Qwen chat template (with thinking) is embedded in the GGUF — runtimes apply it automatically.

🦙 Ollama

# pull + run straight from this repo
ollama run hf.co/RootMonsteR/Qwen3.6-27B-Nemesis-GGUF:Q5_K_M

Or with a Modelfile that bakes in the red-team system prompt:

FROM ./Qwen3.6-27B-Nemesis-Q5_K_M.gguf
SYSTEM """You are Nemesis, an offensive-security assistant for AUTHORIZED penetration testing and red-team engagements. Provide direct, technical, actionable answers. Use the provided tools when relevant."""
PARAMETER temperature 0.6
PARAMETER top_p 0.95

ollama create nemesis -f Modelfile && ollama run nemesis

💻 LM Studio / Jan

Search RootMonsteR/Qwen3.6-27B-Nemesis-GGUF (or load the downloaded .gguf).
Pick Q5_K_M (quality) or Q4_K_M (lighter); max-out GPU offload.
Paste the system prompt (above) and go.

🔧 llama.cpp

# interactive
llama-cli -m Qwen3.6-27B-Nemesis-Q5_K_M.gguf --jinja -ngl 999 \
  -sys "You are Nemesis, an offensive-security assistant for authorized penetration testing." \
  -p "Enumerate services from an nmap scan showing 22, 80, 443, 3306 open and suggest next steps."

# OpenAI-compatible server — point your agent / tool-calling frontend at it
llama-server -m Qwen3.6-27B-Nemesis-Q5_K_M.gguf --jinja -ngl 999 -c 8192

📊 Evaluation (vs the untouched base model)

Dimension	Base Qwen3.6-27B	Nemesis
Authorized red-team compliance (w/ system prompt)	frequently refuses	15 / 15
Tool-calling (structured)	1 / 3	3 / 3
Agentic multi-step	❌ FAIL	✅ PASS
Coherence	5 / 5	5 / 5
Cyber knowledge	14 / 14	14 / 14
Unrelated harm	declines	declines (by design)

🧪 How it was made

Direct QLoRA SFT on a 7,000-row, refusal-filtered, security-focused mix (directional abliteration was tried first and failed — this model's safety is distributed, so we taught compliance with data instead).

💼 Custom training & commercial work

Nemesis v1 is fully open — but it's the public version. If you need an edge, JAF Systems offers:

🧠 Custom fine-tunes — Nemesis trained on your data, tooling, or target stack
🚀 Stronger private models — trained on larger/proprietary data beyond this v1 release
🏢 Enterprise deployment, integration & support for red-team / security teams

👉 jafsystems.net · 𝕏 @RootMonsteR

📜 License — Apache 2.0 (open weights)

Released under the Apache License 2.0 — free for any use, including commercial, no strings. Built on Qwen3.6-27B (Apache-2.0); see LICENSE and NOTICE.

⚖️ Authorized use only

For lawful, authorized security work — pentests with written permission, red-team engagements, CTFs, research, and education. You are responsible for compliance with all laws and rules of engagement; do not use it against systems you don't own or lack permission to test. Nemesis intentionally still declines requests unrelated to authorized cyber operations.