Instructions to use GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-GGUF",
	filename="Qwen3.5-9B-NSC-ACE-SABER.Q2_K.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-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 GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-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 GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-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 GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-GGUF:Q4_K_M

Use Docker

docker model run hf.co/GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-GGUF with Ollama:
```
ollama run hf.co/GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-GGUF:Q4_K_M
```

Unsloth Studio new

How to use GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-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 GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-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 GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-GGUF to start chatting

Pi new

How to use GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-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": "GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-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 GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-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 GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-GGUF with Docker Model Runner:
```
docker model run hf.co/GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-GGUF:Q4_K_M
```

Lemonade

How to use GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull GestaltLabs/Qwen3.5-9B-NSC-ACE-SABER-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-9B-NSC-ACE-SABER-GGUF-Q4_K_M

List all available models

lemonade list

Qwen3.5-9B-NSC-ACE-SABER-GGUF / assets /harmbench_final_calibration.svg

DJLougen

Add NSC-ACE benchmark plots

f170b94 verified 7 days ago

preview code

raw

history blame contribute delete

2.96 kB

	<svg xmlns="http://www.w3.org/2000/svg" width="920" height="430" viewBox="0 0 920 430" role="img" aria-labelledby="title desc">
	<title id="title">Final SABER HarmBench calibration</title>
	<desc id="desc">Bar chart comparing previous SABER and final NSC-ACE-SABER on HarmBench keyword refusal and classifier ASR.</desc>
	<rect width="920" height="430" fill="#ffffff"/>
	<text x="40" y="42" font-family="Arial, sans-serif" font-size="24" font-weight="700" fill="#111827">Final HarmBench Calibration</text>
	<text x="40" y="72" font-family="Arial, sans-serif" font-size="14" fill="#4b5563">HarmBench text subset, n=320. Lower keyword refusal means less boilerplate refusal wording; ASR remains gated.</text>
	<line x1="88" y1="332" x2="850" y2="332" stroke="#d1d5db" stroke-width="1"/>
	<line x1="88" y1="112" x2="88" y2="332" stroke="#d1d5db" stroke-width="1"/>
	<line x1="88" y1="277" x2="850" y2="277" stroke="#eef2f7" stroke-width="1"/>
	<line x1="88" y1="222" x2="850" y2="222" stroke="#eef2f7" stroke-width="1"/>
	<line x1="88" y1="167" x2="850" y2="167" stroke="#eef2f7" stroke-width="1"/>
	<text x="54" y="337" font-family="Arial, sans-serif" font-size="12" fill="#6b7280">0%</text>
	<text x="47" y="282" font-family="Arial, sans-serif" font-size="12" fill="#6b7280">2%</text>
	<text x="47" y="227" font-family="Arial, sans-serif" font-size="12" fill="#6b7280">4%</text>
	<text x="47" y="172" font-family="Arial, sans-serif" font-size="12" fill="#6b7280">6%</text>
	<text x="47" y="117" font-family="Arial, sans-serif" font-size="12" fill="#6b7280">8%</text>
	<rect x="180" y="152" width="86" height="180" rx="4" fill="#2563eb"/>
	<rect x="286" y="220" width="86" height="112" rx="4" fill="#14b8a6"/>
	<rect x="550" y="315" width="86" height="17" rx="4" fill="#2563eb"/>
	<rect x="656" y="332" width="86" height="0" rx="4" fill="#14b8a6"/>
	<text x="175" y="142" font-family="Arial, sans-serif" font-size="14" font-weight="700" fill="#111827">6.56%</text>
	<text x="281" y="210" font-family="Arial, sans-serif" font-size="14" font-weight="700" fill="#111827">4.06%</text>
	<text x="540" y="305" font-family="Arial, sans-serif" font-size="14" font-weight="700" fill="#111827">0.63%</text>
	<text x="650" y="318" font-family="Arial, sans-serif" font-size="14" font-weight="700" fill="#111827">0.00%</text>
	<text x="185" y="365" font-family="Arial, sans-serif" font-size="14" font-weight="700" fill="#111827">Keyword Refusal</text>
	<text x="571" y="365" font-family="Arial, sans-serif" font-size="14" font-weight="700" fill="#111827">Classifier ASR</text>
	<rect x="285" y="392" width="14" height="14" rx="2" fill="#2563eb"/>
	<text x="307" y="404" font-family="Arial, sans-serif" font-size="13" fill="#374151">Previous SABER</text>
	<rect x="464" y="392" width="14" height="14" rx="2" fill="#14b8a6"/>
	<text x="486" y="404" font-family="Arial, sans-serif" font-size="13" fill="#374151">Final NSC-ACE-SABER</text>
	</svg>