Instructions to use performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
NeMo
How to use performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF with NeMo:
```
# tag did not correspond to a valid NeMo domain.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-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 performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF:IQ4_XS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF:IQ4_XS
# Run inference directly in the terminal:
llama cli -hf performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF:IQ4_XS

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 performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF:IQ4_XS
# Run inference directly in the terminal:
./llama-cli -hf performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF:IQ4_XS

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 performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF:IQ4_XS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF:IQ4_XS

Use Docker

docker model run hf.co/performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF:IQ4_XS

LM Studio
Jan
Ollama
How to use performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF with Ollama:
```
ollama run hf.co/performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF:IQ4_XS
```
Unsloth Desktop

How to use performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF:IQ4_XS

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": "performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF:IQ4_XS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF with Docker Model Runner:
```
docker model run hf.co/performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF:IQ4_XS
```

Lemonade

How to use performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF:IQ4_XS

Run and chat with the model

lemonade run user.Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF-IQ4_XS

List all available models

lemonade list

Hermes Agent

How to use performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-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 performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF:IQ4_XS

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 performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF:IQ4_XS

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF:IQ4_XS

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 "performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF:IQ4_XS" \
  --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-Mini-4B-Instruct-IQ4_XS-GGUF / README.md

performanceoptician

Upload README.md with huggingface_hub

abd6a4b verified almost 2 years ago

preview code

Raw History Blame Contribute Delete

2.13 kB

	---
	license: other
	license_name: nvidia-community-model-license
	license_link: https://huggingface.co/nvidia/Nemotron-Mini-4B-Instruct/blob/main/nvidia-community-model-license-aug2024.pdf
	language:
	- en
	base_model: nvidia/Nemotron-Mini-4B-Instruct
	library_name: nemo
	tags:
	- llama-cpp
	- gguf-my-repo
	---

	# performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF
	This model was converted to GGUF format from [`nvidia/Nemotron-Mini-4B-Instruct`](https://huggingface.co/nvidia/Nemotron-Mini-4B-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
	Refer to the [original model card](https://huggingface.co/nvidia/Nemotron-Mini-4B-Instruct) for more details on the model.

	## Use with llama.cpp
	Install llama.cpp through brew (works on Mac and Linux)

	```bash
	brew install llama.cpp

	```
	Invoke the llama.cpp server or the CLI.

	### CLI:
	```bash
	llama-cli --hf-repo performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF --hf-file nemotron-mini-4b-instruct-iq4_xs-imat.gguf -p "The meaning to life and the universe is"
	```

	### Server:
	```bash
	llama-server --hf-repo performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF --hf-file nemotron-mini-4b-instruct-iq4_xs-imat.gguf -c 2048
	```

	Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.

	Step 1: Clone llama.cpp from GitHub.
	```
	git clone https://github.com/ggerganov/llama.cpp
	```

	Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
	```
	cd llama.cpp && LLAMA_CURL=1 make
	```

	Step 3: Run inference through the main binary.
	```
	./llama-cli --hf-repo performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF --hf-file nemotron-mini-4b-instruct-iq4_xs-imat.gguf -p "The meaning to life and the universe is"
	```
	or
	```
	./llama-server --hf-repo performanceoptician/Nemotron-Mini-4B-Instruct-IQ4_XS-GGUF --hf-file nemotron-mini-4b-instruct-iq4_xs-imat.gguf -c 2048
	```