Instructions to use vultr/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-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 vultr/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-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 vultr/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf vultr/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf vultr/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf vultr/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf vultr/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf vultr/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF:Q4_K_M

Use Docker

docker model run hf.co/vultr/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use vultr/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF with Ollama:
```
ollama run hf.co/vultr/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF:Q4_K_M
```
Unsloth Desktop

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vultr/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF:Q4_K_M

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": "vultr/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use vultr/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF with Docker Model Runner:
```
docker model run hf.co/vultr/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF:Q4_K_M
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull vultr/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use vultr/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-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 vultr/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF:Q4_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 vultr/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vultr/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF:Q4_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 "vultr/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF:Q4_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"

Nemotron 3 Nano Omni 30B A3B Reasoning BF16, GGUF

Nvidia Nemotron 3 Nano Omni 30B A3B Reasoning BF16 is a multimodal Mixture-of-Experts reasoning model designed for unified audio, vision, and language understanding, enabling AI agents to efficiently derive insights from videos and documents with high accuracy. The model integrates C-RADIOv4-H based vision and Parakeet audio encoders for efficient long-context processing and precise reasoning, supporting image, video, document, and speech reasoning tasks.

This repository holds Vultr's GGUF quantizations of it. They are hybrid quantizations: rather than applying one precision to the whole network, each layer's precision is chosen from a measured importance score, so the bits go where they change the output most.

Model Overview

Attribute	Value
Base model	nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
Architecture	nemotron_h_moe, Mixture-of-Experts
Parameters	30B
Active parameters	3B
Layers	52
Hidden size	2,688
Attention heads	32
Experts	128 routed, 6 selected per token, shared expert
Context length	up to 256K tokens
Vocabulary	131,072
License	NVIDIA Open Model Agreement

Attribute	Value
Base model	nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
Architecture	nemotron_h_moe, Mixture-of-Experts
Parameters	30B
Active parameters	3B
Layers	52
Hidden size	2,688
Attention heads	32
Experts	128 routed, 6 selected per token, shared expert
Context length	up to 256K tokens
Vocabulary	131,072
License	NVIDIA Open Model Agreement

Quantizations

File	Type	Size	KLD vs bf16
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-Q5_K_M.gguf	Q5_K_M	28.64 GB	0.0074
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-Q4_K_M.gguf	Q4_K_M	26.96 GB	0.0081
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-IQ3_M.gguf	IQ3_M	19.91 GB	0.0196
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-IQ3_S.gguf	IQ3_S	19.72 GB	0.0192

File	Type	Size	KLD vs bf16
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-Q5_K_M.gguf	Q5_K_M	28.64 GB	0.0074
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-Q4_K_M.gguf	Q4_K_M	26.96 GB	0.0081
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-IQ3_M.gguf	IQ3_M	19.91 GB	0.0196
Nemotron-3-Nano-Omni-30B-A3B-Reasoning-IQ3_S.gguf	IQ3_S	19.72 GB	0.0192

The vision encoder is in Nemotron-3-Nano-Omni-30B-A3B-Reasoning-mmproj-f16.gguf (2.99 GB). llama.cpp downloads it automatically with the command under Run, so image input works without extra steps.

KL divergence measures how far a quantized model's next-token probabilities drift from those of the original bf16 model, averaged over every token of the evaluation text. The lower the value, the closer the quantized model is to the original; zero would mean identical output.

Evaluation

Every variant in this repository was evaluated against the original bf16 model for perplexity, KL divergence, top-token agreement, HellaSwag and WinoGrande, under identical conditions. The full results are maintained on the model's page in the Vultr Model Library:

https://docs.vultr.com/models/nvidia-nemotron-v3/nemotron-3-nano-omni-30b-a3b-reasoning?tab=quantized

That page is the reference for these files. The summary above is an excerpt from it.

Run

llama-server -hf vultr/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF:Q4_K_M

The model's chat template is embedded in every file, so no extra prompt formatting is needed.

License

These files are derived from nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 and are distributed under the same license, NVIDIA Open Model Agreement. The model is the work of NVIDIA; Vultr produced the quantizations.

Downloads last month: 133

GGUF

Model size

32B params

Architecture

nemotron_h_moe

Hardware compatibility

3-bit

4-bit

5-bit

Inference Providers NEW

Any-to-Any

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for vultr/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-GGUF

Base model

nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16

Quantized

(53)

this model