Instructions to use tomvaillant/qwen3.5-9b-abliterated-journalist-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tomvaillant/qwen3.5-9b-abliterated-journalist-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tomvaillant/qwen3.5-9b-abliterated-journalist-GGUF",
	filename="model-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

llama.cpp

How to use tomvaillant/qwen3.5-9b-abliterated-journalist-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tomvaillant/qwen3.5-9b-abliterated-journalist-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf tomvaillant/qwen3.5-9b-abliterated-journalist-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 tomvaillant/qwen3.5-9b-abliterated-journalist-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf tomvaillant/qwen3.5-9b-abliterated-journalist-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 tomvaillant/qwen3.5-9b-abliterated-journalist-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf tomvaillant/qwen3.5-9b-abliterated-journalist-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 tomvaillant/qwen3.5-9b-abliterated-journalist-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tomvaillant/qwen3.5-9b-abliterated-journalist-GGUF:Q4_K_M

Use Docker

docker model run hf.co/tomvaillant/qwen3.5-9b-abliterated-journalist-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use tomvaillant/qwen3.5-9b-abliterated-journalist-GGUF with Ollama:
```
ollama run hf.co/tomvaillant/qwen3.5-9b-abliterated-journalist-GGUF:Q4_K_M
```

Unsloth Studio

How to use tomvaillant/qwen3.5-9b-abliterated-journalist-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 tomvaillant/qwen3.5-9b-abliterated-journalist-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 tomvaillant/qwen3.5-9b-abliterated-journalist-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tomvaillant/qwen3.5-9b-abliterated-journalist-GGUF to start chatting

How to use tomvaillant/qwen3.5-9b-abliterated-journalist-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf tomvaillant/qwen3.5-9b-abliterated-journalist-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": "tomvaillant/qwen3.5-9b-abliterated-journalist-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use tomvaillant/qwen3.5-9b-abliterated-journalist-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 tomvaillant/qwen3.5-9b-abliterated-journalist-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 tomvaillant/qwen3.5-9b-abliterated-journalist-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use tomvaillant/qwen3.5-9b-abliterated-journalist-GGUF with Docker Model Runner:
```
docker model run hf.co/tomvaillant/qwen3.5-9b-abliterated-journalist-GGUF:Q4_K_M
```

Lemonade

How to use tomvaillant/qwen3.5-9b-abliterated-journalist-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tomvaillant/qwen3.5-9b-abliterated-journalist-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.qwen3.5-9b-abliterated-journalist-GGUF-Q4_K_M

List all available models

lemonade list

qwen3.5-9b-abliterated-journalist-GGUF

GGUF export of tomvaillant/qwen3.5-9b-abliterated-journalist, an investigative journalism and OSINT fine-tune based on huihui-ai/Huihui-Qwen3.5-9B-abliterated.

Usage

llama-cli -hf tomvaillant/qwen3.5-9b-abliterated-journalist-GGUF --jinja

Files

model-q4_k_m.gguf -- Q4_K_M llama.cpp quantization
chat_template.jinja
tokenizer files

Training

Adapter: tomvaillant/qwen3.5-9b-abliterated-journalist
Merged checkpoint: tomvaillant/qwen3.5-9b-abliterated-journalist-merged
Method: QLoRA with Unsloth + TRL SFT, merged and converted to GGUF
Dataset: tomvaillant/investigative-journalism-training

Sources And Attribution

Training data covers OSINT tool selection, source triangulation, investigative methodology, financial investigation, digital security, ethics, sourcing, media law, and story structure. Sources include tomvaillant/osint-tool-database, Indicator Media briefing data, Buried Signals skill repositories, GIJN, Bellingcat, Verification Handbook 3, SPJ, RCFP, UNESCO, Al Jazeera Media Institute, CiFAR, CIPE, and EJF/TEMPO Institute.

Full attribution is maintained in the training repository as SOURCES.md.

Intended Use

Built for local llama.cpp inference in investigative journalism and OSINT workflows. Treat outputs as leads, not verified findings.

Downloads last month: 395

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for tomvaillant/qwen3.5-9b-abliterated-journalist-GGUF

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

huihui-ai/Huihui-Qwen3.5-9B-abliterated

Quantized

(14)

this model