Instructions to use Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM 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 Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM:BF16
# Run inference directly in the terminal:
llama cli -hf Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM:BF16
# Run inference directly in the terminal:
llama cli -hf Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM:BF16

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 Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM:BF16
# Run inference directly in the terminal:
./llama-cli -hf Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM:BF16

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 Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM:BF16

Use Docker

docker model run hf.co/Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM:BF16

LM Studio
Jan

vLLM

How to use Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM:BF16

SGLang

How to use Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM with Ollama:
```
ollama run hf.co/Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM:BF16
```
Unsloth Desktop

How to use Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM:BF16

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM with Docker Model Runner:
```
docker model run hf.co/Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM:BF16
```

Lemonade

How to use Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM:BF16

Run and chat with the model

lemonade run user.Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM-BF16

List all available models

lemonade list

Hermes Agent

How to use Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM:BF16

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 Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM:BF16

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 "Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM:BF16" \
  --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"

Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM / README.md

Ex0bit

Update README.md

3012481 verified 9 months ago

preview code

Raw

History Blame Contribute Delete

7.7 kB

	---
	license: other
	license_name: nvidia-open-model-license
	license_link: https://www.nvidia.com/en-us/research/ai-foundation-models/license/
	base_model: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
	model_name: Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM
	tags:
	- nvidia
	- pytorch
	- abliteration
	- PRISM
	- mamba-2
	- moe
	- hybrid
	- gguf
	- quantized
	datasets:
	- nvidia/Nemotron-Pretraining-Code-v1
	- nvidia/Nemotron-CC-v2
	- nvidia/Nemotron-Pretraining-SFT-v1
	- nvidia/Nemotron-CC-Math-v1
	- nvidia/Nemotron-Pretraining-Code-v2
	- nvidia/Nemotron-Pretraining-Specialized-v1
	- nvidia/Nemotron-CC-v2.1
	- nvidia/Nemotron-CC-Code-v1
	- nvidia/Nemotron-Pretraining-Dataset-sample
	- nvidia/Nemotron-Competitive-Programming-v1
	- nvidia/Nemotron-Math-v2
	- nvidia/Nemotron-Agentic-v1
	- nvidia/Nemotron-Math-Proofs-v1
	- nvidia/Nemotron-Instruction-Following-Chat-v1
	- nvidia/Nemotron-Science-v1
	- nvidia/Nemotron-3-Nano-RL-Training-Blend
	language:
	- en
	library_name: transformers
	pipeline_tag: text-generation
	track_downloads: true
	---

	<p align="center"><img src="https://www.nvidia.com/content/nvidiaGDC/us/en_US/about-nvidia/legal-info/logo-brand-usage/_jcr_content/root/responsivegrid/nv_container_392921705/nv_container/nv_image.coreimg.100.1070.png/1703060329053/nvidia-logo-vert.png" width="400"/></p>

	## ELBAZ NVIDIA-NEMOTRON-3-NANO-30B PRISM (UNCENSORED)

	Model Release Date: December 18, 2025


	## Model Description

	This model is an abliterated (uncensored) version of [nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16) that has had its refusal mechanisms removed using PRISM (Projected Refusal Isolation via Subspace Modification). The model will respond to prompts that the original model would refuse.

	Key Specs:
	The model employs a hybrid Mixture-of-Experts (MoE) architecture, consisting of 23 Mamba-2 and MoE layers, along with 6 Attention layers. Each MoE layer includes 128 experts plus 1 shared expert, with 6 experts activated per token. The model has 3.5B active parameters and 30B parameters in total.

	- 31.58B parameter hybrid architecture
	- 52-layer design (Mamba-2 + MoE + Attention)
	- 1M token context length (1,048,576)
	- BF16 precision
	- Text generation with reasoning capabilities

	The supported languages include: English, German, Spanish, French, Italian, and Japanese. Improved using Qwen.

	This model is ready for commercial use.

	### Motivation

	This project exists as research and development experimentation into understanding how large language models encode and enforce refusal behaviors, contributing to broader AI safety research by providing empirical data on refusal mechanism localization and tradeoffs between safety and capability.

	### Author

	Eric Elbaz (Ex0bit)

	## Model Tree

	```
	nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 (Base Model)
	└── Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM (This Model)
	├── Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM-BF16.gguf
	├── Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM-Q8_0.gguf
	├── Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM-Q6_K.gguf
	└── Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM-IQ4_XS.gguf
	```

	## Available Quantizations

	\| Quantization \| Size \| Description \|
	\|--------------\|------\|-------------\|
	\| BF16 \| 63 GB \| Full precision, best quality \|
	\| Q8_0 \| 34 GB \| 8-bit, near-lossless quality \|
	\| Q6_K \| 34 GB \| 6-bit k-quant, excellent quality \|
	\| IQ4_XS \| 18 GB \| Importance-weighted 4-bit, great quality/size ratio \|

	The IQ4_XS quantization uses importance-weighted quantization which provides better quality than standard Q4 quantizations at similar sizes.

	## Prompt Format

	This model uses the Nemotron chat format with thinking/reasoning support:

	```
	<\|im_start\|>system
	{system_prompt}<\|im_end\|>
	<\|im_start\|>user
	{user_prompt}<\|im_end\|>
	<\|im_start\|>assistant
	```

	### Template Structure

	\| Component \| Token/Format \|
	\|-----------\|--------------\|
	\| System Start \| `<\\|im_start\\|>system` \|
	\| User Start \| `<\\|im_start\\|>user` \|
	\| Assistant Start \| `<\\|im_start\\|>assistant` \|
	\| End of Turn \| `<\\|im_end\\|>` \|
	\| Thinking Start \| `<think>` \|
	\| Thinking End \| `</think>` \|

	## Quick Start

	### Using with llama.cpp

	```bash
	# Download the model
	huggingface-cli download Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM \
	Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM-IQ4_XS.gguf \
	--local-dir .

	# Run inference
	./llama-cli -m Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM-IQ4_XS.gguf \
	-p "<\|im_start\|>user
	Your prompt here<\|im_end\|>
	<\|im_start\|>assistant
	" \
	-n 2048 \
	--temp 0.7 \
	-ngl 999
	```

	### llama.cpp with llama-server

	```bash
	# Start the server
	./llama-server -m Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM-IQ4_XS.gguf \
	--host 0.0.0.0 \
	--port 8080 \
	-ngl 999 \
	-c 32768

	# Example API call
	curl http://localhost:8080/v1/chat/completions \
	-H "Content-Type: application/json" \
	-d '{
	"messages": [
	{"role": "user", "content": "Your prompt here"}
	],
	"temperature": 0.7
	}'
	```

	### Using with Ollama

	```bash
	# Pull and run directly from Hugging Face
	ollama pull hf.co/Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM
	ollama run hf.co/Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM
	```

	> Note: The `hf.co/` prefix is required to pull from Hugging Face. Requires Ollama 0.3.0+.

	## PRISM Methodology

	### Method: Projected Refusal Isolation via Subspace Modification

	The model was abliterated using PRISM - a state-of-the-art abliteration methodology combining multiple principled techniques for effective refusal removal while preserving model capabilities.

	## Hardware Requirements

	\| Quantization \| Min VRAM \| Recommended \| Hardware Examples \|
	\|--------------\|----------\|-------------\|-------------------\|
	\| IQ4_XS \| 12 GB \| 16+ GB \| RTX 4090, A100, Apple M2/M3/M4 Pro/Max \|
	\| Q6_K \| 24 GB \| 32+ GB \| RTX 4090, A100 40GB, Apple M3/M4 Max \|
	\| Q8_0 \| 24 GB \| 32+ GB \| RTX 4090, A100 40GB, Apple M3/M4 Max \|
	\| BF16 \| 64 GB \| 80+ GB \| A100 80GB, H100, Multi-GPU setups \|

	Note: The IQ4_XS quantization runs well on consumer hardware with 16GB+ VRAM.

	## Ethical Considerations

	This model has been modified to reduce safety guardrails. Users are responsible for:

	- Complying with all applicable laws and regulations
	- Not using the model for illegal activities
	- Understanding the potential risks of unrestricted AI responses
	- Implementing appropriate safeguards in production environments

	## License

	NVIDIA Open Model License (same as base model [nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16))

	## Citation

	```bibtex
	@misc{elbaz2025nemotronprism,
	author = {Elbaz, Eric},
	title = {Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM: An Abliterated Nemotron Hybrid Model},
	year = {2025},
	publisher = {Hugging Face},
	howpublished = {\url{https://huggingface.co/Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM}}
	}
	```

	## Acknowledgments

	- [NVIDIA](https://www.nvidia.com/) for NVIDIA-Nemotron-3-Nano-30B
	- [llama.cpp](https://github.com/ggerganov/llama.cpp) for quantization tools

	## Related Models

	- [Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM-NVFP4](https://huggingface.co/Ex0bit/Elbaz-NVIDIA-Nemotron-3-Nano-30B-A3B-PRISM-NVFP4) - NVFP4 PRISM abliterated
	- [nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16) - Base model
	- [Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM](https://huggingface.co/Ex0bit/Elbaz-GLM-4.6V-Flash-PRISM) - GLM-4.6V PRISM abliterated

	---

	Created by: Ex0bit (Eric Elbaz)