Instructions to use google/gemma-4-31B-it-qat-q4_0-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use google/gemma-4-31B-it-qat-q4_0-gguf with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="google/gemma-4-31B-it-qat-q4_0-gguf")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("google/gemma-4-31B-it-qat-q4_0-gguf", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use google/gemma-4-31B-it-qat-q4_0-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 google/gemma-4-31B-it-qat-q4_0-gguf:Q4_0
# Run inference directly in the terminal:
llama cli -hf google/gemma-4-31B-it-qat-q4_0-gguf:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf google/gemma-4-31B-it-qat-q4_0-gguf:Q4_0
# Run inference directly in the terminal:
llama cli -hf google/gemma-4-31B-it-qat-q4_0-gguf:Q4_0

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 google/gemma-4-31B-it-qat-q4_0-gguf:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf google/gemma-4-31B-it-qat-q4_0-gguf:Q4_0

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 google/gemma-4-31B-it-qat-q4_0-gguf:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf google/gemma-4-31B-it-qat-q4_0-gguf:Q4_0

Use Docker

docker model run hf.co/google/gemma-4-31B-it-qat-q4_0-gguf:Q4_0

LM Studio
Jan

vLLM

How to use google/gemma-4-31B-it-qat-q4_0-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "google/gemma-4-31B-it-qat-q4_0-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "google/gemma-4-31B-it-qat-q4_0-gguf",
		"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/google/gemma-4-31B-it-qat-q4_0-gguf:Q4_0

SGLang

How to use google/gemma-4-31B-it-qat-q4_0-gguf with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "google/gemma-4-31B-it-qat-q4_0-gguf" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "google/gemma-4-31B-it-qat-q4_0-gguf",
		"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 images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "google/gemma-4-31B-it-qat-q4_0-gguf" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "google/gemma-4-31B-it-qat-q4_0-gguf",
		"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"
						}
					}
				]
			}
		]
	}'

Ollama
How to use google/gemma-4-31B-it-qat-q4_0-gguf with Ollama:
```
ollama run hf.co/google/gemma-4-31B-it-qat-q4_0-gguf:Q4_0
```
Unsloth Desktop

How to use google/gemma-4-31B-it-qat-q4_0-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf google/gemma-4-31B-it-qat-q4_0-gguf:Q4_0

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": "google/gemma-4-31B-it-qat-q4_0-gguf:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use google/gemma-4-31B-it-qat-q4_0-gguf with Docker Model Runner:
```
docker model run hf.co/google/gemma-4-31B-it-qat-q4_0-gguf:Q4_0
```

Lemonade

How to use google/gemma-4-31B-it-qat-q4_0-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull google/gemma-4-31B-it-qat-q4_0-gguf:Q4_0

Run and chat with the model

lemonade run user.gemma-4-31B-it-qat-q4_0-gguf-Q4_0

List all available models

lemonade list

Hermes Agent

How to use google/gemma-4-31B-it-qat-q4_0-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 google/gemma-4-31B-it-qat-q4_0-gguf:Q4_0

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 google/gemma-4-31B-it-qat-q4_0-gguf:Q4_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use google/gemma-4-31B-it-qat-q4_0-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf google/gemma-4-31B-it-qat-q4_0-gguf:Q4_0

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 "google/gemma-4-31B-it-qat-q4_0-gguf:Q4_0" \
  --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"

MaartenGr commited on Jul 15

Commit

5b27800

1 Parent(s): 14a8f47

Update README (#6)

Browse files

- Update README (bc00008e1556cbb0e7463746f17cbed83a541027)

Files changed (1) hide show

README.md +6 -5

README.md CHANGED Viewed

@@ -29,6 +29,7 @@ base_model:
 > * **GGUF** (Q4_0): Ready-to-deploy formats for broad ecosystem compatibility. Available for Gemma 4 E2B, E4B, 12B, 26B A4B, and 31B.
 > * **Mobile-optimized** (wNa8o8): A custom schema engineered explicitly for mobile hardware efficiency. It features targeted 2-bit decoding layers, optimized KV caches, and static activations to maximize VRAM savings. Available for Gemma 4 E2B and E4B.
 > * **Compressed Tensors** (w4a16): QAT checkpoints serialized in the compressed-tensors format for native, optimized inference with vLLM. Available for Gemma 4 E2B, E4B, 12B, and 31B.
 Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages.
@@ -144,7 +145,7 @@ Once you have everything installed, you can proceed to load the model with the c
 ```python
 from transformers import AutoProcessor, AutoModelForMultimodalLM
-MODEL_ID = "google/gemma-4-12B-it"
 # Load model
 processor = AutoProcessor.from_pretrained(MODEL_ID)
@@ -199,7 +200,7 @@ You can then load the model with the code below:
 ```python
 from transformers import AutoProcessor, AutoModelForMultimodalLM
-MODEL_ID = "google/gemma-4-12B-it"
 # Load model
 processor = AutoProcessor.from_pretrained(MODEL_ID)
@@ -258,7 +259,7 @@ You can then load the model with the code below:
 ```python
 from transformers import AutoProcessor, AutoModelForMultimodalLM
-MODEL_ID = "google/gemma-4-12B-it"
 # Load model
 processor = AutoProcessor.from_pretrained(MODEL_ID)
@@ -316,7 +317,7 @@ You can then load the model with the code below:
 ```python
 from transformers import AutoProcessor, AutoModelForMultimodalLM
-MODEL_ID = "google/gemma-4-12B-it"
 # Load model
 processor = AutoProcessor.from_pretrained(MODEL_ID)
@@ -391,7 +392,7 @@ Compared to Gemma 3, the models use standard `system`, `assistant`, and `user` r
 ### 3. Multi-Turn Conversations
-* **No Thinking Content in History**: In multi-turn conversations, the historical model output should only include the final response. Thoughts from previous model turns must *not be added* before the next user turn begins.
 ### 4. Modality order

 > * **GGUF** (Q4_0): Ready-to-deploy formats for broad ecosystem compatibility. Available for Gemma 4 E2B, E4B, 12B, 26B A4B, and 31B.
 > * **Mobile-optimized** (wNa8o8): A custom schema engineered explicitly for mobile hardware efficiency. It features targeted 2-bit decoding layers, optimized KV caches, and static activations to maximize VRAM savings. Available for Gemma 4 E2B and E4B.
 > * **Compressed Tensors** (w4a16): QAT checkpoints serialized in the compressed-tensors format for native, optimized inference with vLLM. Available for Gemma 4 E2B, E4B, 12B, and 31B.
+> * **Assistant Compatibility**: When using multi-token prediction (speculative decoding) with an assistant model alongside a QAT target model, the assistant model must also be a QAT checkpoint with the same precision to ensure compatibility.
 Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants. Gemma 4 features a context window of up to 256K tokens and maintains multilingual support in over 140 languages.
 ```python
 from transformers import AutoProcessor, AutoModelForMultimodalLM
+MODEL_ID = "google/gemma-4-31B-it"
 # Load model
 processor = AutoProcessor.from_pretrained(MODEL_ID)
 ```python
 from transformers import AutoProcessor, AutoModelForMultimodalLM
+MODEL_ID = "google/gemma-4-31B-it"
 # Load model
 processor = AutoProcessor.from_pretrained(MODEL_ID)
 ```python
 from transformers import AutoProcessor, AutoModelForMultimodalLM
+MODEL_ID = "google/gemma-4-31B-it"
 # Load model
 processor = AutoProcessor.from_pretrained(MODEL_ID)
 ```python
 from transformers import AutoProcessor, AutoModelForMultimodalLM
+MODEL_ID = "google/gemma-4-31B-it"
 # Load model
 processor = AutoProcessor.from_pretrained(MODEL_ID)
 ### 3. Multi-Turn Conversations
+* **No Thinking Content in History**: In multi-turn conversations, the historical model output should only include the final response. Thoughts from previous model turns must *not be added* before the next user turn begins, with the exception of tool call turns where thinking content should be preserved.
 ### 4. Modality order