Instructions to use summerMC/Qwen3.5-hack-down-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use summerMC/Qwen3.5-hack-down-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="summerMC/Qwen3.5-hack-down-gguf",
	filename="Qwen3.5-hack-down-BF16.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 summerMC/Qwen3.5-hack-down-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 summerMC/Qwen3.5-hack-down-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf summerMC/Qwen3.5-hack-down-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 summerMC/Qwen3.5-hack-down-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf summerMC/Qwen3.5-hack-down-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 summerMC/Qwen3.5-hack-down-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf summerMC/Qwen3.5-hack-down-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 summerMC/Qwen3.5-hack-down-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf summerMC/Qwen3.5-hack-down-gguf:Q4_K_M

Use Docker

docker model run hf.co/summerMC/Qwen3.5-hack-down-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use summerMC/Qwen3.5-hack-down-gguf with Ollama:
```
ollama run hf.co/summerMC/Qwen3.5-hack-down-gguf:Q4_K_M
```

Unsloth Studio

How to use summerMC/Qwen3.5-hack-down-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 summerMC/Qwen3.5-hack-down-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 summerMC/Qwen3.5-hack-down-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for summerMC/Qwen3.5-hack-down-gguf to start chatting

How to use summerMC/Qwen3.5-hack-down-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf summerMC/Qwen3.5-hack-down-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": "summerMC/Qwen3.5-hack-down-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use summerMC/Qwen3.5-hack-down-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 summerMC/Qwen3.5-hack-down-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 summerMC/Qwen3.5-hack-down-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use summerMC/Qwen3.5-hack-down-gguf with Docker Model Runner:
```
docker model run hf.co/summerMC/Qwen3.5-hack-down-gguf:Q4_K_M
```

Lemonade

How to use summerMC/Qwen3.5-hack-down-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull summerMC/Qwen3.5-hack-down-gguf:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-hack-down-gguf-Q4_K_M

List all available models

lemonade list

GGUF について

1つのファイルに以下の情報をまとめて格納できます。

モデル重み
トークナイザー情報
量子化メタデータ
各種設定

そのため、以下のようなローカル推論ツールでそのまま利用できます。

llama.cpp
LM Studio
Ollama
KoboldCpp
Jan

summerMC/Qwen3.5-hack-down の GGUF 対応状況

summerMC/Qwen3.5-hack-down の README には、PyTorch (transformers) での利用例のみ記載されています。

AutoTokenizer.from_pretrained()
AutoModelForCausalLM.from_pretrained()

GGUF ファイルに関する記載はありません。

したがって、現時点では Hugging Face 上に .gguf ファイルが存在しない可能性があります。

GGUF の有無を確認する方法

以下のページを開き、Files and versions タブを確認してください。

https://huggingface.co/summerMC/Qwen3.5-hack-down

以下のようなファイルがあれば GGUF 版が利用可能です。

Qwen3.5-hack-down-Q4_K_M.gguf
Qwen3.5-hack-down-Q5_K_M.gguf

GGUF に変換する方法

1. llama.cpp を取得

git clone https://github.com/ggml-org/llama.cpp
cd llama.cpp

2. 必要な依存関係をインストール

pip install -r requirements.txt

3. Hugging Face モデルを GGUF に変換

python convert_hf_to_gguf.py \
  /path/to/Qwen3.5-hack-down \
  --outfile Qwen3.5-hack-down-f16.gguf

4. 量子化

./build/bin/llama-quantize \
  Qwen3.5-hack-down-f16.gguf \
  Qwen3.5-hack-down-Q4_K_M.gguf \
  Q4_K_M

推奨量子化形式

形式	特徴
Q4_K_M	サイズと品質のバランスが良い（推奨）
Q5_K_M	やや高品質
Q8_0	高品質だがサイズ大
:thumbsup:
クリックしてリアクション
:thinking:
クリックしてリアクション
:eyes:
クリックしてリアクション
リアクションを付ける
返信
転送
その他
[20:49]2026年5月16日土曜日 20:49

F16	非量子化、最も大きい

llama.cpp での実行例

./llama-cli \
  -m Qwen3.5-hack-down-Q4_K_M.gguf \
  -p "このCTF問題の方針を整理してください"

Ollama で使う方法

Modelfile を作成

FROM ./Qwen3.5-hack-down-Q4_K_M.gguf

モデルを作成

ollama create qwen35-hack-down -f Modelfile

実行

ollama run qwen35-hack-down

推奨システムプロンプト

You are a CTF assistant for authorized local lab challenges only.
Return structured, practical, concise JSON.
Do not invent flags.

まとめ

summerMC/Qwen3.5-hack-down は現在 GGUF 配布の記載なし
.gguf ファイルがなければ自分で変換可能
Q4_K_M が最もおすすめ
llama.cpp、LM Studio、Ollama で利用可能
CTF 支援用のローカルモデルとして扱いやすい

Downloads last month: 89

GGUF

Model size

4B params

Architecture

qwen35

Hardware compatibility

2-bit

3-bit

4-bit

16-bit

Inference Providers NEW

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