Instructions to use tatvaAi/gemma-4-E4B-it-IQ4_NL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tatvaAi/gemma-4-E4B-it-IQ4_NL with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tatvaAi/gemma-4-E4B-it-IQ4_NL",
	filename="gemma-4-E4B-it-IQ4_NL.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use tatvaAi/gemma-4-E4B-it-IQ4_NL with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tatvaAi/gemma-4-E4B-it-IQ4_NL:IQ4_NL
# Run inference directly in the terminal:
llama-cli -hf tatvaAi/gemma-4-E4B-it-IQ4_NL:IQ4_NL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tatvaAi/gemma-4-E4B-it-IQ4_NL:IQ4_NL
# Run inference directly in the terminal:
llama-cli -hf tatvaAi/gemma-4-E4B-it-IQ4_NL:IQ4_NL

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 tatvaAi/gemma-4-E4B-it-IQ4_NL:IQ4_NL
# Run inference directly in the terminal:
./llama-cli -hf tatvaAi/gemma-4-E4B-it-IQ4_NL:IQ4_NL

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 tatvaAi/gemma-4-E4B-it-IQ4_NL:IQ4_NL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tatvaAi/gemma-4-E4B-it-IQ4_NL:IQ4_NL

Use Docker

docker model run hf.co/tatvaAi/gemma-4-E4B-it-IQ4_NL:IQ4_NL

LM Studio
Jan

vLLM

How to use tatvaAi/gemma-4-E4B-it-IQ4_NL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tatvaAi/gemma-4-E4B-it-IQ4_NL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tatvaAi/gemma-4-E4B-it-IQ4_NL",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tatvaAi/gemma-4-E4B-it-IQ4_NL:IQ4_NL

Ollama
How to use tatvaAi/gemma-4-E4B-it-IQ4_NL with Ollama:
```
ollama run hf.co/tatvaAi/gemma-4-E4B-it-IQ4_NL:IQ4_NL
```

Unsloth Studio new

How to use tatvaAi/gemma-4-E4B-it-IQ4_NL 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 tatvaAi/gemma-4-E4B-it-IQ4_NL 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 tatvaAi/gemma-4-E4B-it-IQ4_NL to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tatvaAi/gemma-4-E4B-it-IQ4_NL to start chatting

Pi new

How to use tatvaAi/gemma-4-E4B-it-IQ4_NL with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf tatvaAi/gemma-4-E4B-it-IQ4_NL:IQ4_NL

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": "tatvaAi/gemma-4-E4B-it-IQ4_NL:IQ4_NL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use tatvaAi/gemma-4-E4B-it-IQ4_NL with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf tatvaAi/gemma-4-E4B-it-IQ4_NL:IQ4_NL

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 tatvaAi/gemma-4-E4B-it-IQ4_NL:IQ4_NL

Run Hermes

hermes

Docker Model Runner
How to use tatvaAi/gemma-4-E4B-it-IQ4_NL with Docker Model Runner:
```
docker model run hf.co/tatvaAi/gemma-4-E4B-it-IQ4_NL:IQ4_NL
```

Lemonade

How to use tatvaAi/gemma-4-E4B-it-IQ4_NL with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tatvaAi/gemma-4-E4B-it-IQ4_NL:IQ4_NL

Run and chat with the model

lemonade run user.gemma-4-E4B-it-IQ4_NL-IQ4_NL

List all available models

lemonade list

Gemma 4 E4B IT – GGUF (IQ4_NL)

🔷 Model Overview

This repository contains a GGUF IQ4_NLconversion of:

Base Model: gemma-4-e4b-it
Developer: Google
Format: GGUF (optimized for llama.cpp)
Precision: IQ4_NL

This model is designed for high-quality local inference.

📦 Files

File	Description
`gemma-4-e4b-it-IQ4_NL.gguf`	IQ4_NL full-precision GGUF model

⚙️ Technical Details

Parameter	Value
Architecture	gemma-4-e4b-it
Format	GGUF
Precision	IQ4_NL
Runtime	llama.cpp
Use Case	High-quality inference

⚡ Why GGUF?

GGUF enables:

Efficient CPU inference via llama.cpp
Single-file model distribution
Fast loading using memory mapping
Cross-platform compatibility

⚠️ License & Usage

This is a converted derivative model.

You must comply with the original license:
👉 https://huggingface.co/google/gemma-4-e4b-it

Important:

❌ Not an official Google release
❌ No additional rights granted
✅ Original model ownership remains with Google
⚠️ Use responsibly under original license terms

🚀 Quick Start (llama.cpp)

./llama-cli -m gemma-4-e4b-it-IQ4_NL.gguf -p "Explain AI simply"

Downloads last month: 44

GGUF

Model size

8B params

Architecture

gemma4

Hardware compatibility

4-bit