Instructions to use WhiskyAKM/Gemma-4-E2B-it-qat-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use WhiskyAKM/Gemma-4-E2B-it-qat-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 WhiskyAKM/Gemma-4-E2B-it-qat-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf WhiskyAKM/Gemma-4-E2B-it-qat-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf WhiskyAKM/Gemma-4-E2B-it-qat-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf WhiskyAKM/Gemma-4-E2B-it-qat-GGUF: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 WhiskyAKM/Gemma-4-E2B-it-qat-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf WhiskyAKM/Gemma-4-E2B-it-qat-GGUF: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 WhiskyAKM/Gemma-4-E2B-it-qat-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf WhiskyAKM/Gemma-4-E2B-it-qat-GGUF:Q4_K_M

Use Docker

docker model run hf.co/WhiskyAKM/Gemma-4-E2B-it-qat-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use WhiskyAKM/Gemma-4-E2B-it-qat-GGUF with Ollama:
```
ollama run hf.co/WhiskyAKM/Gemma-4-E2B-it-qat-GGUF:Q4_K_M
```

Unsloth Studio

How to use WhiskyAKM/Gemma-4-E2B-it-qat-GGUF 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 WhiskyAKM/Gemma-4-E2B-it-qat-GGUF 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 WhiskyAKM/Gemma-4-E2B-it-qat-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for WhiskyAKM/Gemma-4-E2B-it-qat-GGUF to start chatting

How to use WhiskyAKM/Gemma-4-E2B-it-qat-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf WhiskyAKM/Gemma-4-E2B-it-qat-GGUF:Q4_K_M

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": "WhiskyAKM/Gemma-4-E2B-it-qat-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use WhiskyAKM/Gemma-4-E2B-it-qat-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf WhiskyAKM/Gemma-4-E2B-it-qat-GGUF: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 "WhiskyAKM/Gemma-4-E2B-it-qat-GGUF: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"

Docker Model Runner
How to use WhiskyAKM/Gemma-4-E2B-it-qat-GGUF with Docker Model Runner:
```
docker model run hf.co/WhiskyAKM/Gemma-4-E2B-it-qat-GGUF:Q4_K_M
```

Lemonade

How to use WhiskyAKM/Gemma-4-E2B-it-qat-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull WhiskyAKM/Gemma-4-E2B-it-qat-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Gemma-4-E2B-it-qat-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use WhiskyAKM/Gemma-4-E2B-it-qat-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 WhiskyAKM/Gemma-4-E2B-it-qat-GGUF: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 WhiskyAKM/Gemma-4-E2B-it-qat-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

Gemma 4 E2B IT QAT — GGUF

GGUF quantizations of google/gemma-4-E2B-it-qat-q4-0, created from the Quantization-Aware Training (QAT) checkpoint of Gemma 4 E2B IT.

Model Overview

Gemma 4 E2B IT is a multimodal model built by Google DeepMind that handles text, image, and audio inputs and generates text output. It is designed for efficient on-device deployment on laptops and mobile devices.

The "E" in E2B stands for "effective" parameters — the model uses Per-Layer Embeddings (PLE) to maximize parameter efficiency, giving each decoder layer its own small embedding for every token. This keeps the effective parameter count much smaller than the total.

This repository contains GGUF conversions of the QAT-optimized checkpoint, making it usable with llama.cpp and other GGUF-compatible inference engines.

Model Architecture

Property	Value
Architecture	Gemma4ForConditionalGeneration
Effective Parameters	2.3B (5.1B with embeddings)
Layers	35
Sliding Window	512 tokens
Context Length	128K tokens
Vocabulary Size	262K
Supported Modalities	Text, Image, Audio
Vision Encoder Parameters	~150M
Audio Encoder Parameters	~300M
Attention	Hybrid (sliding window + global, every 5th layer)
RoPE	Proportional RoPE (p-RoPE) on global layers

GGUF Files

File	Format	Size	Description
`gemma-4-E2B-it-qat-Q4_0.gguf`	Q4_0	3.2G	QAT Q4_0 — native QAT quantization
`gemma-4-E2B-it-qat-Q4_K_M.gguf`	Q4_K_M	3.2G	K-quant, medium
`gemma-4-E2B-it-qat-Q4_K_S.gguf`	Q4_K_S	3.2G	K-quant, small
`gemma-4-E2B-it-qat-Q5_K_M.gguf`	Q5_K_M	3.4G	K-quant, medium
`gemma-4-E2B-it-qat-Q5_K_S.gguf`	Q5_K_S	3.4G	K-quant, small
`gemma-4-E2B-it-qat-Q6_K.gguf`	Q6_K	3.6G	K-quant, higher precision
`gemma-4-E2B-it-qat-Q8_0.gguf`	Q8_0	4.7G	8-bit, highest GGUF precision
`gemma-4-E2B-it-qat-bf16.gguf`	bf16	8.7G	Full bfloat16 (unquantized)
`gemma-4-E2B-it-qat-bf16-Q4_0.gguf`	Q4_0	42M	Q4_0 weights only (no embeddings)

A chat_template.jinja file is also provided for use with chat-based inference.

Note on QAT: The Q4_0 file is the native QAT quantization. The K-quant and Q8_0 variants are additional GGUF quantizations produced from the QAT checkpoint. The QAT optimization preserves quality close to bfloat16 while dramatically reducing memory requirements.

Usage

llama.cpp (CLI)

# Run text inference
./llama-cli \
  -m gemma-4-E2B-it-qat-Q4_0.gguf \
  -p "Explain quantum computing in simple terms." \
  --temp 1.0 --top-k 64 --top-p 0.95

llama-server (OpenAI-compatible API)

./llama-server \
  -m gemma-4-E2B-it-qat-Q4_0.gguf \
  --host 0.0.0.0 --port 8080

Multimodal (Image / Audio)

For image and audio inputs, use a GGUF-compatible engine with multimodal support. Refer to your inference engine's documentation for passing image/audio data alongside text prompts.

Modality order tip: For best results, place image content before text and audio content after text in your prompt.

Generation Parameters

Recommended parameters from the model's generation_config.json:

Parameter	Value
Temperature	1.0
Top-K	64
Top-P	0.95
BOS Token ID	2
EOS Token IDs	1, 106, 50
Pad Token ID	0

Thinking Mode

Gemma 4 supports configurable thinking (reasoning) mode:

Enable: Include the <|think|> token at the start of the system prompt.
Output format: When thinking is enabled, the model outputs internal reasoning followed by the final answer:
```
<|channel>thought
[Internal reasoning]
<channel|>
[Final answer]
```
Disable: Omit the <|think|> token. For the E2B variant, thinking is fully off when disabled (no empty thought block is generated).

Many libraries like Transformers and llama.cpp handle the chat template complexities automatically.

Key Features

Multimodal: Text, image, and audio understanding
Long Context: 128K token context window
Function Calling: Native support for structured tool use (agentic workflows)
Multilingual: Support for 140+ languages
On-Device Optimized: Designed for efficient local execution on laptops and mobile devices
Native System Prompt: Supports the system role for structured conversations

Acknowledgements

Original model: google/gemma-4-E2B-it
QAT checkpoint: google/gemma-4-E2B-it-qat-q4-0
Technical report: Gemma 4 Technical Report (arXiv:2607.02770)

Citation

@misc{gemmateam2026gemma4,
      title={Gemma 4 Technical Report},
      author={Gemma Team},
      year={2026},
      eprint={2607.02770},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2607.02770},
}