Instructions to use FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF",
	filename="gemma-4-E4B-it-qat-mxfp4.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-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 FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF
# Run inference directly in the terminal:
llama cli -hf FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF
# Run inference directly in the terminal:
llama cli -hf FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF

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 FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF
# Run inference directly in the terminal:
./llama-cli -hf FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF

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 FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF

Use Docker

docker model run hf.co/FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF

LM Studio
Jan
Ollama
How to use FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF with Ollama:
```
ollama run hf.co/FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF
```

Unsloth Studio

How to use FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-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 FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-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 FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF to start chatting

How to use FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF

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": "FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-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 FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF

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 FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF

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 "FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF" \
  --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 FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF with Docker Model Runner:
```
docker model run hf.co/FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF
```

Lemonade

How to use FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF

Run and chat with the model

lemonade run user.Gemma-4-E4B-it-QAT-MXFP4-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

Gemma 4 E4B Instruct - QAT + MXFP4 Hybrid GGUF

QAT-optimized weights preserved at Q4_0, overhead tensors quantized to MXFP4.

What Makes This Different

This is a hybrid quantization of Google official QAT (Quantization-Aware Training) model. Instead of requantizing the Q4_0 weights (which breaks QAT benefits and vision quality), we:

Kept all weight tensors at Q4_0 - attention, FFN, embeddings - exactly as Google trained them
Quantized only the F32 norm/bias tensors to MXFP4 - these are the overhead tensors (layer norms, RMS norms, etc.)
Used Google QAT mmproj - the vision projector trained alongside the QAT model

Why Standard MXFP4 from QAT Breaks Vision

Google QAT model was specifically trained to be resilient to Q4_0 quantization patterns. The weight values learned during QAT compensate for Q4_0 rounding. When you requantize Q4_0 -> F32 -> MXFP4, a second round of quantization error is introduced that QAT training did not account for. Vision tokens flow through the same attention/FFN layers - precision loss disproportionately degrades vision.

How the Hybrid Approach Works

Using llama-quantize --tensor-type-file with --allow-requantize:

llama-quantize --allow-requantize --tensor-type-file keep_q4.txt input.gguf output.gguf MXFP4

The tensor-type-file lists all Q4_0/Q4_K tensors to keep at their current type. When the quantizer sees cur_type == new_type, it copies the tensor data as-is - zero precision loss. Only the remaining F32 tensors are quantized to MXFP4.

Usage

# llama.cpp
llama-server -m gemma-4-E4B-it-qat-mxfp4.gguf --mmproj mmproj-gemma-4-E4B-it-qat.gguf -ngl 99

Source

Base model: google/gemma-4-E4B-it-qat-q4_0-unquantized
Quantized with: llama.cpp build 537 (commit d2c6795)
Chat template: Native Gemma 4 (thinking enabled by default)
Vision: Full multimodal support via QAT mmproj

Files

File	Description
gemma-4-E4B-it-qat-mxfp4.gguf	Q4_0 weights + MXFP4 norms
mmproj-gemma-4-E4B-it-qat.gguf	QAT vision projector

License

Apache 2.0 (same as base model)

Downloads last month: 161

GGUF

Model size

7B params

Architecture

gemma4

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for FreedomAISVR/Gemma-4-E4B-it-QAT-MXFP4-GGUF

Base model

google/gemma-4-E4B

Finetuned

google/gemma-4-E4B-it

Finetuned

google/gemma-4-E4B-it-qat-q4_0-unquantized

Quantized

(31)

this model