Instructions to use oyildirim/CyberStrike-OffSec-35B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use oyildirim/CyberStrike-OffSec-35B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="oyildirim/CyberStrike-OffSec-35B-GGUF",
	filename="CyberStrike-OffSec-35B-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use oyildirim/CyberStrike-OffSec-35B-GGUF 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 oyildirim/CyberStrike-OffSec-35B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf oyildirim/CyberStrike-OffSec-35B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf oyildirim/CyberStrike-OffSec-35B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf oyildirim/CyberStrike-OffSec-35B-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 oyildirim/CyberStrike-OffSec-35B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf oyildirim/CyberStrike-OffSec-35B-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 oyildirim/CyberStrike-OffSec-35B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf oyildirim/CyberStrike-OffSec-35B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/oyildirim/CyberStrike-OffSec-35B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use oyildirim/CyberStrike-OffSec-35B-GGUF with Ollama:
```
ollama run hf.co/oyildirim/CyberStrike-OffSec-35B-GGUF:Q4_K_M
```

Unsloth Studio

How to use oyildirim/CyberStrike-OffSec-35B-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 oyildirim/CyberStrike-OffSec-35B-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 oyildirim/CyberStrike-OffSec-35B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for oyildirim/CyberStrike-OffSec-35B-GGUF to start chatting

How to use oyildirim/CyberStrike-OffSec-35B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf oyildirim/CyberStrike-OffSec-35B-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": "oyildirim/CyberStrike-OffSec-35B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use oyildirim/CyberStrike-OffSec-35B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf oyildirim/CyberStrike-OffSec-35B-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 oyildirim/CyberStrike-OffSec-35B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use oyildirim/CyberStrike-OffSec-35B-GGUF with Docker Model Runner:
```
docker model run hf.co/oyildirim/CyberStrike-OffSec-35B-GGUF:Q4_K_M
```

Lemonade

How to use oyildirim/CyberStrike-OffSec-35B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull oyildirim/CyberStrike-OffSec-35B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.CyberStrike-OffSec-35B-GGUF-Q4_K_M

List all available models

lemonade list

CyberStrike-OffSec-35B-GGUF

GGUF Quantized Versions for llama.cpp, Ollama & LM Studio

Available Quantizations

File	Quant	Size	BPW	Quality	Use Case
`CyberStrike-OffSec-35B-Q8_0.gguf`	Q8_0	36 GB	8.52	Best	Highest quality, 48+ GB VRAM
`CyberStrike-OffSec-35B-Q6_K.gguf`	Q6_K	27 GB	6.58	Excellent	Near-lossless, 32+ GB VRAM
`CyberStrike-OffSec-35B-Q5_K_M.gguf`	Q5_K_M	24 GB	5.71	Very Good	Most popular, 32 GB VRAM
`CyberStrike-OffSec-35B-Q4_K_M.gguf`	Q4_K_M	21 GB	4.89	Good	Best balance, 24+ GB VRAM

How to Download

Ollama (Easiest)

# Run directly — downloads automatically
ollama run hf.co/oyildirim/CyberStrike-OffSec-35B-GGUF:Q5_K_M

HuggingFace CLI

pip install huggingface_hub

# Download a specific quantization
hf download oyildirim/CyberStrike-OffSec-35B-GGUF CyberStrike-OffSec-35B-Q5_K_M.gguf

LM Studio

Search for oyildirim/CyberStrike-OffSec-35B-GGUF in the model browser, select the quantization you want, and click download.

Direct URL

https://huggingface.co/oyildirim/CyberStrike-OffSec-35B-GGUF/resolve/main/CyberStrike-OffSec-35B-Q5_K_M.gguf

Replace Q5_K_M with Q4_K_M, Q6_K, or Q8_0 for other quantizations.

Usage

Ollama

ollama run hf.co/oyildirim/CyberStrike-OffSec-35B-GGUF:Q5_K_M

Or with a custom Modelfile:

cat > Modelfile << 'EOF'
FROM ./CyberStrike-OffSec-35B-Q5_K_M.gguf

PARAMETER temperature 0.7
PARAMETER top_p 0.9

SYSTEM "You are CyberStrike, an elite offensive security AI assistant."
EOF

ollama create cyberstrike -f Modelfile
ollama run cyberstrike

llama.cpp

# Run directly from HuggingFace
./llama-cli -hf oyildirim/CyberStrike-OffSec-35B-GGUF \
  -hff CyberStrike-OffSec-35B-Q5_K_M.gguf \
  -p "Explain SSRF exploitation in cloud environments" \
  -n 512 --temp 0.7

# Or with a local file
./llama-cli -m CyberStrike-OffSec-35B-Q5_K_M.gguf \
  -p "Explain SSRF exploitation in cloud environments" \
  -n 512 --temp 0.7

LM Studio

Download any GGUF file and load it directly in LM Studio.

Benchmark Results (Full Precision)

Benchmark	Score	Rank
SecEval (9 domains)	81.39%	#1
MITRE ATT&CK (MAET)	93.94%	#1
CWE Knowledge (CWET)	93.05%	#1
CyberMetric-10000	86.61%	#4
MMLU Computer Security	86.00%	-

Base Model

See the full model card at oyildirim/CyberStrike-OffSec-35B for complete benchmark results, training details, and architecture information.

Built with purpose. Benchmarked with rigor. Designed for professionals.

Downloads last month: 28

GGUF

Model size

36B params

Architecture

qwen35moe

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for oyildirim/CyberStrike-OffSec-35B-GGUF

Base model

Qwen/Qwen3.6-35B-A3B

Finetuned

oyildirim/CyberStrike-OffSec-35B

Quantized

(2)

this model