Instructions to use t-firefly/gemma4-e2b-rknn3-rk1820 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use t-firefly/gemma4-e2b-rknn3-rk1820 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 t-firefly/gemma4-e2b-rknn3-rk1820
# Run inference directly in the terminal:
llama cli -hf t-firefly/gemma4-e2b-rknn3-rk1820

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf t-firefly/gemma4-e2b-rknn3-rk1820
# Run inference directly in the terminal:
llama cli -hf t-firefly/gemma4-e2b-rknn3-rk1820

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 t-firefly/gemma4-e2b-rknn3-rk1820
# Run inference directly in the terminal:
./llama-cli -hf t-firefly/gemma4-e2b-rknn3-rk1820

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 t-firefly/gemma4-e2b-rknn3-rk1820
# Run inference directly in the terminal:
./build/bin/llama-cli -hf t-firefly/gemma4-e2b-rknn3-rk1820

Use Docker

docker model run hf.co/t-firefly/gemma4-e2b-rknn3-rk1820

LM Studio
Jan
Ollama
How to use t-firefly/gemma4-e2b-rknn3-rk1820 with Ollama:
```
ollama run hf.co/t-firefly/gemma4-e2b-rknn3-rk1820
```
Unsloth Desktop

How to use t-firefly/gemma4-e2b-rknn3-rk1820 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf t-firefly/gemma4-e2b-rknn3-rk1820

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": "t-firefly/gemma4-e2b-rknn3-rk1820"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use t-firefly/gemma4-e2b-rknn3-rk1820 with Docker Model Runner:
```
docker model run hf.co/t-firefly/gemma4-e2b-rknn3-rk1820
```

Lemonade

How to use t-firefly/gemma4-e2b-rknn3-rk1820 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull t-firefly/gemma4-e2b-rknn3-rk1820

Run and chat with the model

lemonade run user.gemma4-e2b-rknn3-rk1820-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use t-firefly/gemma4-e2b-rknn3-rk1820 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf t-firefly/gemma4-e2b-rknn3-rk1820

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 t-firefly/gemma4-e2b-rknn3-rk1820

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use t-firefly/gemma4-e2b-rknn3-rk1820 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf t-firefly/gemma4-e2b-rknn3-rk1820

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 "t-firefly/gemma4-e2b-rknn3-rk1820" \
  --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"

Gemma 4 E2B IT

RK1820 | LlamaPi Ready

Model Overview

Item	Details
Original model	Gemma 4 E2B IT (ModelScope \| Hugging Face)
Original developer	Google DeepMind
Model type	Multimodal generation
Target platform	RK1820
Converted by	Firefly AI Team
Deployment tool	LlamaPi

Run with LlamaPi

llamapi run gemma4:e2b

llamapi run handles model download, loading, and execution. See the LlamaPi Wiki for setup and usage.

About the Original Model

Gemma 4 E2B IT is a compact instruction-tuned multimodal model developed by Google DeepMind.

Accepts text, image, and audio inputs and generates text output with an encoder-free unified architecture.
Supports reasoning, coding, multilingual, and agentic tasks with a 256K context window and 140+ languages.
Designed as an efficient open model for on-device and edge deployment.

License & Attribution

The models provided in this repository are converted and adapted by the Firefly AI team from the original models. All intellectual property rights and copyright in the underlying original models remain with the original official team, and their distribution is governed by the corresponding official open-source license.