Instructions to use RoundRobin237/Gemma4-E2B-Dflash2-Android with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use RoundRobin237/Gemma4-E2B-Dflash2-Android 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 RoundRobin237/Gemma4-E2B-Dflash2-Android:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RoundRobin237/Gemma4-E2B-Dflash2-Android:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RoundRobin237/Gemma4-E2B-Dflash2-Android:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RoundRobin237/Gemma4-E2B-Dflash2-Android: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 RoundRobin237/Gemma4-E2B-Dflash2-Android:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RoundRobin237/Gemma4-E2B-Dflash2-Android: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 RoundRobin237/Gemma4-E2B-Dflash2-Android:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RoundRobin237/Gemma4-E2B-Dflash2-Android:Q4_K_M

Use Docker

docker model run hf.co/RoundRobin237/Gemma4-E2B-Dflash2-Android:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use RoundRobin237/Gemma4-E2B-Dflash2-Android with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RoundRobin237/Gemma4-E2B-Dflash2-Android"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RoundRobin237/Gemma4-E2B-Dflash2-Android",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/RoundRobin237/Gemma4-E2B-Dflash2-Android:Q4_K_M

Ollama
How to use RoundRobin237/Gemma4-E2B-Dflash2-Android with Ollama:
```
ollama run hf.co/RoundRobin237/Gemma4-E2B-Dflash2-Android:Q4_K_M
```
Unsloth Desktop

How to use RoundRobin237/Gemma4-E2B-Dflash2-Android with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RoundRobin237/Gemma4-E2B-Dflash2-Android:Q4_K_M

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": "RoundRobin237/Gemma4-E2B-Dflash2-Android:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use RoundRobin237/Gemma4-E2B-Dflash2-Android with Docker Model Runner:
```
docker model run hf.co/RoundRobin237/Gemma4-E2B-Dflash2-Android:Q4_K_M
```

Lemonade

How to use RoundRobin237/Gemma4-E2B-Dflash2-Android with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RoundRobin237/Gemma4-E2B-Dflash2-Android:Q4_K_M

Run and chat with the model

lemonade run user.Gemma4-E2B-Dflash2-Android-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use RoundRobin237/Gemma4-E2B-Dflash2-Android with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RoundRobin237/Gemma4-E2B-Dflash2-Android:Q4_K_M

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 RoundRobin237/Gemma4-E2B-Dflash2-Android:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use RoundRobin237/Gemma4-E2B-Dflash2-Android with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RoundRobin237/Gemma4-E2B-Dflash2-Android:Q4_K_M

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 "RoundRobin237/Gemma4-E2B-Dflash2-Android:Q4_K_M" \
  --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"

Gemma4-E2B-Dflash2-Android / NOTICE

RoundRobin237

Publish Gemma E2B BF16, Q4 GGUF and RaInfer NPU DFlash2 assets

77e134b verified 12 days ago

Raw History Blame Contribute Delete

1.63 kB

Gemma4-E2B-Dflash2-Android

Model weights: Apache License 2.0. Original Gemma 4 E2B instruction-tuned model
Copyright Google; https://huggingface.co/google/gemma-4-E2B-it
Original weights are redistributed unchanged. The unmodified Q4 GGUF is from
https://huggingface.co/unsloth/gemma-4-E2B-it-GGUF (Apache-2.0).
The compatible mmproj is an external download from that upstream repository;
it is not redistributed in this package. Google provides the original weights.

Modified artifacts: mixed-precision quantization, QNN compilation, intermediate
feature outputs, portable vision-embedding operator alias, CPU drafter training
and packaging. These are independent preparations, not official Google,
Qualcomm, Unsloth or Z Lab releases. Detailed source revisions and changes are
recorded in provenance.json and quantization.json.

DFlash2-derived grouped dynamic-convolution/selection components are based on
https://github.com/z-lab/dflash at 07ebd93db9f472af339b644bb70221ad8428328a,
Copyright (c) 2026 Z Lab, MIT. The locally trained draft weights are distinct
from upstream checkpoints; algorithm lineage does not imply endorsement.
Full MIT notice is retained in licenses/DFlash-MIT.txt.

RaInfer engine source: https://github.com/LEPTONNW/RaInfer, MIT.
llama.cpp/mtmd source: https://github.com/ggml-org/llama.cpp, MIT.
ExecuTorch source: https://github.com/pytorch/executorch, BSD-3-Clause.
Separate license texts are preserved in licenses/ for attribution. Engine
sources, applications, binaries and proprietary SDK/runtime files are not
distributed in this model package. Their respective licenses remain separate.

	Gemma4-E2B-Dflash2-Android

	Model weights: Apache License 2.0. Original Gemma 4 E2B instruction-tuned model
	Copyright Google; https://huggingface.co/google/gemma-4-E2B-it
	Original weights are redistributed unchanged. The unmodified Q4 GGUF is from
	https://huggingface.co/unsloth/gemma-4-E2B-it-GGUF (Apache-2.0).
	The compatible mmproj is an external download from that upstream repository;
	it is not redistributed in this package. Google provides the original weights.

	Modified artifacts: mixed-precision quantization, QNN compilation, intermediate
	feature outputs, portable vision-embedding operator alias, CPU drafter training
	and packaging. These are independent preparations, not official Google,
	Qualcomm, Unsloth or Z Lab releases. Detailed source revisions and changes are
	recorded in provenance.json and quantization.json.

	DFlash2-derived grouped dynamic-convolution/selection components are based on
	https://github.com/z-lab/dflash at 07ebd93db9f472af339b644bb70221ad8428328a,
	Copyright (c) 2026 Z Lab, MIT. The locally trained draft weights are distinct
	from upstream checkpoints; algorithm lineage does not imply endorsement.
	Full MIT notice is retained in licenses/DFlash-MIT.txt.

	RaInfer engine source: https://github.com/LEPTONNW/RaInfer, MIT.
	llama.cpp/mtmd source: https://github.com/ggml-org/llama.cpp, MIT.
	ExecuTorch source: https://github.com/pytorch/executorch, BSD-3-Clause.
	Separate license texts are preserved in licenses/ for attribution. Engine
	sources, applications, binaries and proprietary SDK/runtime files are not
	distributed in this model package. Their respective licenses remain separate.