Instructions to use Avarok/nvidia-nemotron-nano-12b-v2-q4_k_m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Avarok/nvidia-nemotron-nano-12b-v2-q4_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 Avarok/nvidia-nemotron-nano-12b-v2-q4_k_m
# Run inference directly in the terminal:
llama cli -hf Avarok/nvidia-nemotron-nano-12b-v2-q4_k_m

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Avarok/nvidia-nemotron-nano-12b-v2-q4_k_m
# Run inference directly in the terminal:
llama cli -hf Avarok/nvidia-nemotron-nano-12b-v2-q4_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 Avarok/nvidia-nemotron-nano-12b-v2-q4_k_m
# Run inference directly in the terminal:
./llama-cli -hf Avarok/nvidia-nemotron-nano-12b-v2-q4_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 Avarok/nvidia-nemotron-nano-12b-v2-q4_k_m
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Avarok/nvidia-nemotron-nano-12b-v2-q4_k_m

Use Docker

docker model run hf.co/Avarok/nvidia-nemotron-nano-12b-v2-q4_k_m

LM Studio
Jan
Ollama
How to use Avarok/nvidia-nemotron-nano-12b-v2-q4_k_m with Ollama:
```
ollama run hf.co/Avarok/nvidia-nemotron-nano-12b-v2-q4_k_m
```

Unsloth Studio

How to use Avarok/nvidia-nemotron-nano-12b-v2-q4_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 Avarok/nvidia-nemotron-nano-12b-v2-q4_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 Avarok/nvidia-nemotron-nano-12b-v2-q4_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 Avarok/nvidia-nemotron-nano-12b-v2-q4_k_m to start chatting

How to use Avarok/nvidia-nemotron-nano-12b-v2-q4_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 Avarok/nvidia-nemotron-nano-12b-v2-q4_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": "Avarok/nvidia-nemotron-nano-12b-v2-q4_k_m"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Avarok/nvidia-nemotron-nano-12b-v2-q4_k_m with Docker Model Runner:
```
docker model run hf.co/Avarok/nvidia-nemotron-nano-12b-v2-q4_k_m
```

Lemonade

How to use Avarok/nvidia-nemotron-nano-12b-v2-q4_k_m with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Avarok/nvidia-nemotron-nano-12b-v2-q4_k_m

Run and chat with the model

lemonade run user.nvidia-nemotron-nano-12b-v2-q4_k_m-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use Avarok/nvidia-nemotron-nano-12b-v2-q4_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 Avarok/nvidia-nemotron-nano-12b-v2-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 Avarok/nvidia-nemotron-nano-12b-v2-q4_k_m

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Avarok/nvidia-nemotron-nano-12b-v2-q4_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 Avarok/nvidia-nemotron-nano-12b-v2-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 "Avarok/nvidia-nemotron-nano-12b-v2-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"

Configuration Parsing Warning:Invalid JSON for config file config.json

NVIDIA Nemotron Nano 12B v2 - GGUF Q4_K_M (7GB)

This repository provides a 4-bit quantized GGUF build of NVIDIA Nemotron Nano 12B v2 using Q4_K_M, reducing the on-disk size to approximately 7GB from roughly 23GB for the original full precision weights, while preserving core capabilities.

Upstream base model: nvidia/NVIDIA-Nemotron-Nano-12B-v2

SHA256: 82ea4805d2f9f37e3c67b06768141ff58e43fb0dcd3983a82e9c2f481eb7fea8

What's included

model-q4.gguf (7.0GB)
tokenizer.json
tokenizer_config.json
special_tokens_map.json
config.json
generation_config.json
configuration_nemotron_h.py
modeling_nemotron_h.py
nemotron_toolcall_parser_no_streaming.py
bias.md, explainability.md, privacy.md, safety.md
acc-vs-budget.png
README.md

Capabilities

✓ Tool calling support via preserved special tokens and helper parser script
✓ Thinking mode tokens for structured reasoning
✓ Long-context up to 128k window
✓ Multilingual general-purpose LLM behavior

Note: GGUF inference backends may vary in their native support for tool-calling integrations; use the included parser or your own orchestration as needed.

Hardware notes

Disk space: 8GB free recommended for the quantized file and metadata
CPU inference: 16GB RAM recommended for 4k contexts; 32GB suggested for comfortable operation. For 128k contexts, memory usage grows significantly and 64 to 128GB system RAM may be required
GPU offload: 8 to 16GB VRAM can accelerate decoding with llama.cpp -ngl offloading; very long contexts may require 24 to 48GB VRAM or hybrid CPU plus GPU offload
Throughput: Depends on backend, threads, and offload settings

Usage

llama.cpp

Build llama.cpp, then run:

Generate:

./llama-cli -m model-q4.gguf -p "Hello, Nemotron." -n 128 -t 8 -c 4096 -ngl 35

Server:

./llama-server -m model-q4.gguf -c 4096 -ngl 35

For very long contexts, increase -c accordingly and ensure sufficient RAM or VRAM for KV cache.

Python via llama-cpp-python

pip install llama-cpp-python

from llama_cpp import Llama
llm = Llama(model_path="model-q4.gguf", n_ctx=4096, n_threads=8)
out = llm("Write a short greeting.", max_tokens=128)
print(out)

Ollama

Create a Modelfile referencing this repo, then create and run:

Modelfile:

FROM hf.co/Avarok/nvidia-nemotron-nano-12b-v2-q4_k_m
PARAMETER num_ctx 4096

Commands:

ollama create nemotron-nano-12b-q4km -f Modelfile
ollama run nemotron-nano-12b-q4km

Note: Ollama versions and syntax may evolve; consult Ollama docs if the Modelfile interface changes.

License and attribution

Base model: NVIDIA Nemotron Nano 12B v2
License: This GGUF quantized derivative is subject to the original model's license and terms. See the upstream model card and license. By using this repository you agree to comply with NVIDIA's licensing for Nemotron models
Attribution: If you use this model, please attribute both NVIDIA for the base model and this repository for the quantized packaging

Reproducibility

This artifact was produced by converting the upstream weights to GGUF and quantizing with Q4_K_M. An equivalent quantization command with llama.cpp tools is:

llama-quantize input.gguf model-q4.gguf Q4_K_M

Exact commands may differ based on the conversion workflow for the upstream model version.

Safety

Review the included bias, privacy, and safety documents. As with all LLMs, outputs may be inaccurate or unsafe without proper safeguards and human oversight.