Instructions to use noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF",
	filename="NVIDIA-Nemotron-3-Nano-30B-A3B-MXFP4_MOE.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-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 noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF:MXFP4_MOE
# Run inference directly in the terminal:
llama cli -hf noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF:MXFP4_MOE

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF:MXFP4_MOE
# Run inference directly in the terminal:
llama cli -hf noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF:MXFP4_MOE

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 noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF:MXFP4_MOE
# Run inference directly in the terminal:
./llama-cli -hf noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF:MXFP4_MOE

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 noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF:MXFP4_MOE
# Run inference directly in the terminal:
./build/bin/llama-cli -hf noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF:MXFP4_MOE

Use Docker

docker model run hf.co/noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF:MXFP4_MOE

LM Studio
Jan

vLLM

How to use noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-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": "noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF:MXFP4_MOE

Ollama
How to use noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF with Ollama:
```
ollama run hf.co/noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF:MXFP4_MOE
```

Unsloth Studio

How to use noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-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 noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-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 noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF to start chatting

How to use noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF:MXFP4_MOE

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": "noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF:MXFP4_MOE"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-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 noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF:MXFP4_MOE

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 noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF:MXFP4_MOE

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF with Docker Model Runner:
```
docker model run hf.co/noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF:MXFP4_MOE
```

Lemonade

How to use noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull noctrex/Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF:MXFP4_MOE

Run and chat with the model

lemonade run user.Nemotron-3-Nano-30B-A3B-MXFP4_MOE-GGUF-MXFP4_MOE

List all available models

lemonade list

surprising performance, thx!

by dexgeh - opened Jan 8

Discussion

dexgeh

Jan 8

I get ~37t/s in tg e ~60t/s in pp (less than 2gb of ram and 7.2gb of vram on startup) on my pc (5800x, 32gb ddr4, rtx3080ti 12gb) with this settings:

llama-server \
  --model NVIDIA-Nemotron-3-Nano-30B-A3B-MXFP4_MOE.gguf \
  --ctx-size 524288 \
  --batch-size 4096 \
  --temp 1.0 \
  --top-p 1.0 \
  --top-k 20 \
  --repeat-penalty 1.05 \
  --gpu-layers 99 \
  --threads 12 \
  --threads-batch 16 \
  --cpu-moe \
  --flash-attn on \
  $*

with --reasoning-budget 0 for coding with opencode is pretty fast.
It's the fastest model on this size that I have used so far on my limited hardware.
Thank you very much for your effort, very appreciated!

noctrex

Owner Jan 9

•

edited Jan 9

Thanks for the kind words, but I just quantize the model, it's nothing special. All the credit goes to the work of the model creators for making such a good model.
Also, you disable the thinking? Won't that make it worse for opencode?

noctrex

Owner Jan 9

Also, from the following guide: https://unsloth.ai/docs/models/nemotron-3
they say that NVIDIA recommends these settings for inference:

General chat/instruction (default):

temperature = 1.0
top_p = 1.0

Tool calling use-cases:

temperature = 0.6
top_p = 0.95

Have you tried these settings for tools in opencode? maybe it will be better

dexgeh

Jan 9

I use thinking for reasoning on the project and preparing documents, often with the llama web interface if i want something fast or anythingllm or jan (i'm still searching for better alternatives).
On opencode I just do "do this" "do that" but not the planning/reasoning because it often lead to very large sessions and i see a decay in speed when i go past 150k tokens in 1h of session; disabling the reasoning reduce the context a lot (let's say 40-50k in 1h).
The alternative is doing a lot of new sessions.

For the parameters I took them in an example on the HF page of the nvidia model, I didn't experiment a lot with them since the quality of the responses is good.

I started doing this stuff like 10 days ago, so i'm still learning.

minyor25

Feb 14

Wow, with 1M context and full offloading to the rtx 3090 it thinks and shits decent code at 150 t/s.

llama-server -m models/NVIDIA-Nemotron-3-Nano-30B-A3B-MXFP4_MOE.gguf
-ctk q8_0 -ctv q4_0 --ctx-size 1048576 --mlock -tb 1 --jinja --temp 0.6 --top-p 0.95 --fit on

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