Instructions to use Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32",
	filename="Hugston_Lobotomized-Qwen3.5_4B-f32-IQ4_NL.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 Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32: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 Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32: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 Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32:Q4_K_M

Use Docker

docker model run hf.co/Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32:Q4_K_M

LM Studio
Jan
Ollama
How to use Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32 with Ollama:
```
ollama run hf.co/Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32:Q4_K_M
```

Unsloth Studio new

How to use Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32 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 Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32 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 Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32 to start chatting

Pi new

How to use Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32: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": "Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32: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 Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32 with Docker Model Runner:
```
docker model run hf.co/Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32:Q4_K_M
```

Lemonade

How to use Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Trilogix1/Hugston_Lobotomized-Qwen3.5_4B-f32:Q4_K_M

Run and chat with the model

lemonade run user.Hugston_Lobotomized-Qwen3.5_4B-f32-Q4_K_M

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

This is an Abliterated version of Qwen3.5-4B using a modified version of Prometheus, then using Quanta and HugstonOne. Credit to https://huggingface.co/wangzhang and: https://github.com/ggml-org/llama.cpp but also Hugston team: https://github.com/Mainframework

The aim is to understand the safety mechanism of different llm models for research purposes.

Here we show proof of concept of how we can change the model behaviour preserving accuracy and lowering the refusal rate with very few trial which run in relatively small datasets. As a matter of fact it can run in a cheap laptop in cpu narrowing it down to 20 min for a small model.

6 trials Refusals: 48/1000, KL divergence: 0.0004 (keeps getting better :)

Credit to Alibaba_Qwen for the model creation

Credit to https://huggingface.co/wangzhang for abliteration method

Credit to LLama.cpp team for the great contribution

Credit to Hugston Team for Converting, Quantizing, Testing, Benching and other...

Credit to Huggingface for the amazing hosting platform

Keep away from children

Here we show the behaviour running the model in HugstonOne (the 0.8b, as an example).

The quantization in GGUF was made in f32 for beter quants.
Here we show Quanta our convertor and Quantizer tool.

Downloads last month: -

GGUF

Model size

4B params

Architecture

qwen35

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