Instructions to use altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF 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 altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF
# Run inference directly in the terminal:
llama cli -hf altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF

Install from WinGet (Windows)

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

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 altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF
# Run inference directly in the terminal:
./llama-cli -hf altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF

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 altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF

Use Docker

docker model run hf.co/altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF

Llama new
LM Studio
Jan

vLLM

How to use altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF

Ollama
How to use altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF with Ollama:
```
ollama run hf.co/altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF
```
Unsloth Desktop

How to use altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF

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": "altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF with Docker Model Runner:
```
docker model run hf.co/altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF
```

Lemonade

How to use altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF

Run and chat with the model

lemonade run user.Nemotron-3-Nano-30B-A3B-XXL-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF

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 altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF

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 "altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF" \
  --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"

Nemotron-3-Nano-30B-A3B

GGUF quant of https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 with full precision applied to attention & ssm related layers for better performance.

I spent soooo much time quantizing this model. I was unsure if it is that broken or I do something wrong. Looks like all Mamba related layers should be in full precision and model have some problems with halucinations and tool colling what is likely result of not good enought datasets used for trainings and overtraining on select topics. This is the only model capable of tool colling that have problems to choose opened (viwed) file in RooCode test. It can inject facts from previous conversation to last reply if it is about simmilar topic, so there are some context understanding related issues also. Regarding halucynations, give it text with Donald Trump. Is he previous president? Is Karol Nawrocki Andrzej Duda? To be fair, this is first good model from Nvidia but still misses here and there.

Maybe I could make this quant even better but I already spent sooooo much time on it and wanted to keep it bellow 30GB. I give up, this one is quite ok and better then other quants I tested.

Downloads last month: 51

GGUF

Model size

32B params

Architecture

nemotron_h_moe

Hardware compatibility

Model tree for altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF

Base model

nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

Quantized

(72)

this model

Datasets used to train altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF

Collection including altomek/Nemotron-3-Nano-30B-A3B-XXL-GGUF

XXL GGUF

Collection

Inspired by Unsloth XL quants, I started mastering my own GGUF quants with gool to make them even better then XL ones. • 13 items • Updated Apr 18