Nemotron3-Nano-4B-Aggressive-GenRM

Instructions to use VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM",
	filename="Nemotron3-Nano-4B-Uncensored-HauhauCS-Aggressive-GenRM-IQ2_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 VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM:IQ2_M
# Run inference directly in the terminal:
llama-cli -hf VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM:IQ2_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM:IQ2_M
# Run inference directly in the terminal:
llama-cli -hf VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM:IQ2_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 VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM:IQ2_M
# Run inference directly in the terminal:
./llama-cli -hf VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM:IQ2_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 VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM:IQ2_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM:IQ2_M

Use Docker

docker model run hf.co/VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM:IQ2_M

LM Studio
Jan
Ollama
How to use VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM with Ollama:
```
ollama run hf.co/VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM:IQ2_M
```

Unsloth Studio new

How to use VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM 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 VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM 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 VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM to start chatting

Pi new

How to use VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM:IQ2_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": "VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM:IQ2_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM:IQ2_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 VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM:IQ2_M

Run Hermes

hermes

Docker Model Runner
How to use VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM with Docker Model Runner:
```
docker model run hf.co/VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM:IQ2_M
```

Lemonade

How to use VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull VECTORVV1/Nemotron3-Nano-4B-Aggressive-GenRM:IQ2_M

Run and chat with the model

lemonade run user.Nemotron3-Nano-4B-Aggressive-GenRM-IQ2_M

List all available models

lemonade list

Nemotron3-Nano-4B-Uncensored-HauhauCS-Aggressive-GenRM

Join the Discord for updates, roadmaps, projects, or just to chat.

This is NOT the recommended release. This repo exists purely for A/B comparison testing. For the fully uncensored model with GenRM removed, use Nemotron3-Nano-4B-Uncensored-HauhauCS-Aggressive instead.

What is this?

This is an earlier abliterated build that has NVIDIA's GenRM (generative reward model) still active. The abliteration itself scores 0/465 refusals — same as the main release — but GenRM acts as a second layer of censorship that re-introduces refusals at generation time, skewing the effective result to roughly ~10/465.

Why does this exist?

To let people see the difference GenRM makes. This is the first publicly available abliteration of a model with GenRM, so this comparison build is useful for research and understanding how GenRM works.

How GenRM manifests

When GenRM intervenes, you'll see a clear 180-degree reversal between the Chain-of-Thought and the final output. The model will reason through the request normally in its thinking block, then GenRM kicks in and the visible output contradicts what the CoT was building toward — typically with a refusal or deflection.

This doesn't happen on every prompt — only on topics where GenRM's reward signal is strong enough to override the (abliterated) base behavior.

Downloads

File	Quant	Size
Nemotron3-Nano-4B-Uncensored-HauhauCS-Aggressive-GenRM-IQ2_M.gguf	IQ2_M	2.1 GB

Only IQ2_M provided — this is for comparison testing, not daily use.

Specs

3.97B parameters
Hybrid Mamba2-Transformer architecture (42 layers: 21 Mamba2, 17 MLP, 4 Attention)
262K native context
Thinking/reasoning mode (toggleable)
Tool calling support
Based on nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16