Instructions to use NexaAI/gemma-3n with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use NexaAI/gemma-3n 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 NexaAI/gemma-3n:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NexaAI/gemma-3n:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf NexaAI/gemma-3n:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf NexaAI/gemma-3n: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 NexaAI/gemma-3n:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf NexaAI/gemma-3n: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 NexaAI/gemma-3n:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf NexaAI/gemma-3n:Q4_K_M

Use Docker

docker model run hf.co/NexaAI/gemma-3n:Q4_K_M

LM Studio
Jan
Ollama
How to use NexaAI/gemma-3n with Ollama:
```
ollama run hf.co/NexaAI/gemma-3n:Q4_K_M
```

Unsloth Studio

How to use NexaAI/gemma-3n 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 NexaAI/gemma-3n 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 NexaAI/gemma-3n to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for NexaAI/gemma-3n to start chatting

Atomic Chat new
Docker Model Runner
How to use NexaAI/gemma-3n with Docker Model Runner:
```
docker model run hf.co/NexaAI/gemma-3n:Q4_K_M
```

Lemonade

How to use NexaAI/gemma-3n with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull NexaAI/gemma-3n:Q4_K_M

Run and chat with the model

lemonade run user.gemma-3n-Q4_K_M

List all available models

lemonade list

gemma-3n / README.md

zackli4ai

Update README.md

850d1cd verified 11 months ago

preview code

Raw

History Blame Contribute Delete

2.01 kB

	# Gemma-3n-E4B-IT

	## Model Description
	Gemma 3n E4B-IT, developed by Google DeepMind, is a 4-billion-parameter efficient multimodal model.
	Built with MatFormer architecture and dynamic parameter activation, it delivers strong text, image, audio, and video understanding while remaining lightweight enough for on-device deployment.
	It supports a 32K context window and multilingual inputs across more than 140 languages.

	## Features
	- Multimodal input: text, image (up to 768×768), audio, and video.
	- Efficient design: parameter skipping and caching enable deployment on edge devices.
	- Large context window: up to 32K tokens.
	- Multilingual: trained on 140+ languages.
	- Compact but strong: achieves benchmark scores competitive with much larger models.

	## Use Cases
	- Visual question answering and captioning
	- Conversational agents with multimodal inputs
	- On-device assistants for mobile and embedded systems
	- Multilingual summarization, translation, and transcription

	## Inputs and Outputs
	Input:
	- Text prompts or dialogue
	- Single image (tokenized for processing)
	- Multiple image inputs and audio inputs support coming soon!

	Output:
	- Generated text (answers, captions, translations, summaries)

	---
	## How to use

	### 1) Install Nexa-SDK
	Download and follow the steps under "Deploy Section" Nexa's model page: [Download Windows SDK](https://sdk.nexa.ai/model/SDXL-Base)

	### 2) Get an access token
	Create a token in the Model Hub, then log in:
	```bash
	nexa config set license '<access_token>'
	```

	### 3) Run the model
	Running:
	```bash
	nexa infer NexaAI/gemma-3n
	```
	---

	## License
	- Licensed under Google’s Gemma terms of use. See Hugging Face model card for details.

	## References
	- [Hugging Face: google/gemma-3n-E4B-it](https://huggingface.co/google/gemma-3n-E4B-it)
	- [Gemma 3n documentation](https://ai.google.dev/gemma/docs/gemma-3n)
	- [Google AI blog announcement](https://developers.googleblog.com/en/introducing-gemma-3n-developer-guide/)