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

Libraries

How to use unsloth/Nemotron-3-Nano-30B-A3B-GGUF with Transformers:

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use unsloth/Nemotron-3-Nano-30B-A3B-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 unsloth/Nemotron-3-Nano-30B-A3B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/Nemotron-3-Nano-30B-A3B-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/Nemotron-3-Nano-30B-A3B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/Nemotron-3-Nano-30B-A3B-GGUF:UD-Q4_K_XL

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 unsloth/Nemotron-3-Nano-30B-A3B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/Nemotron-3-Nano-30B-A3B-GGUF:UD-Q4_K_XL

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 unsloth/Nemotron-3-Nano-30B-A3B-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/Nemotron-3-Nano-30B-A3B-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/Nemotron-3-Nano-30B-A3B-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/Nemotron-3-Nano-30B-A3B-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": "unsloth/Nemotron-3-Nano-30B-A3B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/Nemotron-3-Nano-30B-A3B-GGUF:UD-Q4_K_XL

SGLang

How to use unsloth/Nemotron-3-Nano-30B-A3B-GGUF 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 "unsloth/Nemotron-3-Nano-30B-A3B-GGUF" \
    --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": "unsloth/Nemotron-3-Nano-30B-A3B-GGUF",
		"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 "unsloth/Nemotron-3-Nano-30B-A3B-GGUF" \
        --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": "unsloth/Nemotron-3-Nano-30B-A3B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use unsloth/Nemotron-3-Nano-30B-A3B-GGUF with Ollama:
```
ollama run hf.co/unsloth/Nemotron-3-Nano-30B-A3B-GGUF:UD-Q4_K_XL
```

Unsloth Studio

How to use unsloth/Nemotron-3-Nano-30B-A3B-GGUF 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 unsloth/Nemotron-3-Nano-30B-A3B-GGUF 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 unsloth/Nemotron-3-Nano-30B-A3B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

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

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/Nemotron-3-Nano-30B-A3B-GGUF:UD-Q4_K_XL

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": "unsloth/Nemotron-3-Nano-30B-A3B-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/Nemotron-3-Nano-30B-A3B-GGUF:UD-Q4_K_XL

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 "unsloth/Nemotron-3-Nano-30B-A3B-GGUF:UD-Q4_K_XL" \
  --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 unsloth/Nemotron-3-Nano-30B-A3B-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/Nemotron-3-Nano-30B-A3B-GGUF:UD-Q4_K_XL
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/Nemotron-3-Nano-30B-A3B-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.Nemotron-3-Nano-30B-A3B-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Hermes Agent

How to use unsloth/Nemotron-3-Nano-30B-A3B-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 unsloth/Nemotron-3-Nano-30B-A3B-GGUF:UD-Q4_K_XL

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 unsloth/Nemotron-3-Nano-30B-A3B-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat

Should UD-Q6_K_XL identical to Q6_K.gguf?

by BVEsun - opened Dec 16, 2025

Discussion

BVEsun

Dec 16, 2025

Nemotron-3-Nano-30B-A3B-Q6_K.gguf
SHA256:
f19626879b433941214bdfe10d7a709ce3488bb7eeee03827f864fa39e6cd166
Pointer size:
136 Bytes
·
Size of remote file:
33.5 GB
·
Xet hash:
567ab9542d8af15b1a78e5827bcb75c1f8f859bf23def5c08b888e18892415fc

Nemotron-3-Nano-30B-A3B-UD-Q6_K_XL.gguf
SHA256:
f19626879b433941214bdfe10d7a709ce3488bb7eeee03827f864fa39e6cd166
Pointer size:
136 Bytes
·
Size of remote file:
33.5 GB
·
Xet hash:
567ab9542d8af15b1a78e5827bcb75c1f8f859bf23def5c08b888e18892415fc

BVEsun changed discussion title from Should Q6_K_XL identical to Q6_K.gguf? to Should UD-Q6_K_XL identical to Q6_K.gguf? Dec 16, 2025

danielhanchen

Unsloth AI org Dec 16, 2025

This is because the model has an architecture like gpt-oss where some dimensions aren't divisible by 128 so some cannot be quantized to lower bits and thus bigger.

That's also why we deleted some 1-bit and 2-bit sizes because they were exactly the same size.

I would recommend using the XL one

BVEsun

Dec 16, 2025

Thank you very much! I'll download the XL one then.

TobDeBer

Dec 16, 2025

This is because the model has an architecture like gpt-oss where some dimensions aren't divisible by 128 so some cannot be quantized to lower bits and thus bigger.

That's also why we deleted some 1-bit and 2-bit sizes because they were exactly the same size.

I would recommend using the XL one

What is the solution?
Add padding support to llama cpp?
Add 64 and 128 weight type variants of low quant?

cmp-nct

Dec 17, 2025

•

edited Dec 17, 2025

Sorry for the duplicate issue, I didn't read this one.
The problem is much less Q6K, the problem is that anything below 4 bit is not available. So the model is being blocked from < 24GB cards.

When I implemented the new released Falcon architecture for llama.cpp I ran into that issue, it's been a while.
The quantization issue, back then also cuda inference was partly blocked, was that the tensor had to be divisible by 256 I believe.
It was no big problem to change that division factor - that's mostly just constants, the smaller blocksize likely introduces a bit of a quantization error increase. I can't recall.
Another option probably is tensor padding like Todeber said.

Changing the constant to a smaller one was very simple, it was my solution for all but one tensor back then. But GGUF had it hardcoded, so it broke compatibility.

TobDeBer

Dec 17, 2025

I'm "working" on a PR to allow arbitrary dimensions with 256 block size.
I'm testing out a vibe coding tool for that right now but if it fails I do it myself.
https://github.com/708-145/llama.cpp/pull/33/files

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment