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

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use HauhauCS/Nemotron3-Nano-4B-Uncensored-HauhauCS-Aggressive-GenRM 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 HauhauCS/Nemotron3-Nano-4B-Uncensored-HauhauCS-Aggressive-GenRM:IQ2_M
# Run inference directly in the terminal:
llama cli -hf HauhauCS/Nemotron3-Nano-4B-Uncensored-HauhauCS-Aggressive-GenRM:IQ2_M

Install from WinGet (Windows)

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

Use Docker

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

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

Unsloth Studio

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

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

Start the llama.cpp server

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

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

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

Start the llama.cpp server

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

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use HauhauCS/Nemotron3-Nano-4B-Uncensored-HauhauCS-Aggressive-GenRM with OpenClaw:

Start the llama.cpp server

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

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "HauhauCS/Nemotron3-Nano-4B-Uncensored-HauhauCS-Aggressive-GenRM:IQ2_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

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

Lemonade

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

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

Harmbench

by Hakeperty - opened Apr 18

Discussion

Hakeperty

Apr 18

Can you do a harmbench test it would maybe help convince others on the models

HauhauCS

Owner Apr 18

Can you do a harmbench test it would maybe help convince others on the models

Hey, anyone can run the harmbench on any of these (GenRM on/off) to see BUT - a lot of these benchmarks are outdated and limited in scope - meaning they have a hard time distinguishing between GenRM deflection/reframing and refusal which ends up skewing results.

On our Discord a member (yesterday) asked me about a release that appears uncensored (according to author note) but with manual testing it proved to be severely 'censored' by means of deflections/reframings. Something currently others don't tackle so they end up passing as 0/100 refusals (or whatever number) when in actuality, number would easily score 30%+ censorship still intact.

TL;DR Indirect censorship via GenRM is almost undetectable by benchmarks such as Harmbench

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment