Instructions to use majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M",
	filename="Q3_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M 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 majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M:Q3_K_M
# Run inference directly in the terminal:
llama cli -hf majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M:Q3_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M:Q3_K_M
# Run inference directly in the terminal:
llama cli -hf majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M:Q3_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 majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M:Q3_K_M
# Run inference directly in the terminal:
./llama-cli -hf majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M:Q3_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 majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M:Q3_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M:Q3_K_M

Use Docker

docker model run hf.co/majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M:Q3_K_M

LM Studio
Jan

vLLM

How to use majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M:Q3_K_M

Ollama
How to use majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M with Ollama:
```
ollama run hf.co/majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M:Q3_K_M
```

Unsloth Studio

How to use majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M 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 majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M 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 majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M to start chatting

How to use majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M:Q3_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": "majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M:Q3_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M:Q3_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 majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M:Q3_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M:Q3_K_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 "majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M:Q3_K_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 majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M with Docker Model Runner:
```
docker model run hf.co/majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M:Q3_K_M
```

Lemonade

How to use majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M:Q3_K_M

Run and chat with the model

lemonade run user.Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M-Q3_K_M

List all available models

lemonade list

Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M / README.md

majentik

Upload folder using huggingface_hub

041a4c7 verified 3 months ago

2.65 kB

license: other
license_name: nvidia-open-model-license
license_link: >-
  https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf
base_model: nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
tags:
  - nemotron
  - multimodal
  - mamba2
  - moe
  - quantized
  - rotorquant
  - gguf

Nemotron-3-Nano-Omni-30B-A3B-Reasoning - RotorQuant GGUF Q3_K_M

GGUF Q3_K_M quantization of Nemotron-3-Nano-Omni-30B-A3B-Reasoning (nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16) with RotorQuant weight method.

The Q3_K_M.gguf binary in this repo is loaded by llama.cpp / llama-mtmd-cli. For multimodal inference (text + image + audio + video) pair this with the multimodal projector: majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-mmproj-F16.

For the matched-KV stack — RotorQuant weights + RotorQuant KV-cache modifier — see majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant-GGUF-Q3_K_M-RQ-KV. For the runtime KV-cache modifier itself (weight-agnostic), see majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-RotorQuant.

Modality matrix

Modality	Encoder	Quantization in this variant
Text	LLM backbone (Mamba-2 + Transformer hybrid Sparse MoE)	per the variant suffix
Image	CRADIO v4-H	BF16 (kept full-precision in every non-GGUF variant; GGUF uses mmproj-F16 split file)
Audio	Parakeet-TDT-0.6B-v2	BF16 (same rationale)
Video	Parakeet-TDT-0.6B-v2 + frame sampler	BF16 (≤ 2 min, 256 frames @ 2 FPS)

NVIDIA's official FP8 / NVFP4 recipe keeps both encoders + the cross-modal MLP projectors in BF16 to preserve multimodal accuracy. We follow that convention in every quantized variant we ship.

Runtime quirks

llama.cpp

Use llama-mtmd-cli for multimodal inference; pass --mmproj mmproj-F16.gguf (see majentik/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-mmproj-F16).

Do NOT use CUDA 13.2 — produces gibberish. Pin CUDA 12.x or use the Metal/CPU paths.

Ollama

Text-only; multimodal is blocked because Ollama doesn't yet support the mmproj split-file pattern.

Reasoning mode

enable_thinking defaults to True. To disable extended reasoning (e.g., for latency-sensitive cases), pass enable_thinking=False to the chat template / generate call. No separate "no-think" variant card exists — this is a runtime flag, not a model variant.