Instructions to use ggml-org/gemma-4-31B-it-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 ggml-org/gemma-4-31B-it-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 ggml-org/gemma-4-31B-it-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf ggml-org/gemma-4-31B-it-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ggml-org/gemma-4-31B-it-GGUF:BF16
# Run inference directly in the terminal:
llama cli -hf ggml-org/gemma-4-31B-it-GGUF:BF16

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 ggml-org/gemma-4-31B-it-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf ggml-org/gemma-4-31B-it-GGUF:BF16

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 ggml-org/gemma-4-31B-it-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ggml-org/gemma-4-31B-it-GGUF:BF16

Use Docker

docker model run hf.co/ggml-org/gemma-4-31B-it-GGUF:BF16

LM Studio
Jan

vLLM

How to use ggml-org/gemma-4-31B-it-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ggml-org/gemma-4-31B-it-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": "ggml-org/gemma-4-31B-it-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/ggml-org/gemma-4-31B-it-GGUF:BF16

Ollama
How to use ggml-org/gemma-4-31B-it-GGUF with Ollama:
```
ollama run hf.co/ggml-org/gemma-4-31B-it-GGUF:BF16
```

Unsloth Studio

How to use ggml-org/gemma-4-31B-it-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 ggml-org/gemma-4-31B-it-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 ggml-org/gemma-4-31B-it-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ggml-org/gemma-4-31B-it-GGUF to start chatting

How to use ggml-org/gemma-4-31B-it-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ggml-org/gemma-4-31B-it-GGUF:BF16

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": "ggml-org/gemma-4-31B-it-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ggml-org/gemma-4-31B-it-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 ggml-org/gemma-4-31B-it-GGUF:BF16

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 ggml-org/gemma-4-31B-it-GGUF:BF16

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use ggml-org/gemma-4-31B-it-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ggml-org/gemma-4-31B-it-GGUF:BF16

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 "ggml-org/gemma-4-31B-it-GGUF:BF16" \
  --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 ggml-org/gemma-4-31B-it-GGUF with Docker Model Runner:
```
docker model run hf.co/ggml-org/gemma-4-31B-it-GGUF:BF16
```

Lemonade

How to use ggml-org/gemma-4-31B-it-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ggml-org/gemma-4-31B-it-GGUF:BF16

Run and chat with the model

lemonade run user.gemma-4-31B-it-GGUF-BF16

List all available models

lemonade list

ggerganov HF Staff commited on 18 days ago

Commit

ab18c06

verified ·

1 Parent(s): fb5801c

Upload folder using huggingface_hub

Browse files

Files changed (14) hide show

.gitattributes +8 -0
.src_sha +5 -0
README.md +19 -5
convert.log +0 -0
dflash-gemma-4-31B-it-BF16.gguf +3 -0
dflash-gemma-4-31B-it-Q8_0.gguf +3 -0
gemma-4-31B-it-BF16.gguf +3 -0
gemma-4-31B-it-Q4_0.gguf +3 -0
gemma-4-31B-it-Q8_0.gguf +2 -2
mmproj-gemma-4-31B-it-BF16.gguf +3 -0
mmproj-gemma-4-31B-it-Q8_0.gguf +2 -2
mtp-gemma-4-31B-it-BF16.gguf +3 -0
mtp-gemma-4-31B-it-Q4_0.gguf +3 -0
mtp-gemma-4-31B-it-Q8_0.gguf +3 -0

@@ -40,3 +40,11 @@ mmproj-gemma-4-31B-it-f16.gguf filter=lfs diff=lfs merge=lfs -text
 gemma-4-31B-it-bf16.gguf filter=lfs diff=lfs merge=lfs -text
 mmproj-gemma-4-31B-it-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 mmproj-gemma-4-31B-it-bf16.gguf filter=lfs diff=lfs merge=lfs -text

 gemma-4-31B-it-bf16.gguf filter=lfs diff=lfs merge=lfs -text
 mmproj-gemma-4-31B-it-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
 mmproj-gemma-4-31B-it-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+dflash-gemma-4-31B-it-BF16.gguf filter=lfs diff=lfs merge=lfs -text
+dflash-gemma-4-31B-it-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-4-31B-it-BF16.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-4-31B-it-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+mmproj-gemma-4-31B-it-BF16.gguf filter=lfs diff=lfs merge=lfs -text
+mtp-gemma-4-31B-it-BF16.gguf filter=lfs diff=lfs merge=lfs -text
+mtp-gemma-4-31B-it-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+mtp-gemma-4-31B-it-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

+ASSISTANT=627c5ec1458b9086b841a91e0512fd31fd2fbbf1
+DFLASH=eabd648301ce28583cc14757912e5e0f84e152e1
+PRIMARY=b9ea41a2887d8607f594846523f94c6cc75ac8a4
+QAT_Q4_0=cd038d02f1f83f6316894fb308286f80c49cd15f
+QAT_Q4_0_UNQUANTIZED=5b965a079e0d4c7ef079027f5e98daf1fa1b4985

@@ -1,13 +1,27 @@
 ---
 base_model:
 - google/gemma-4-31B-it
 ---
-# gemma-4-31B-it-GGUF
-Recommended way to run this model:
-```sh
-llama-server -hf ggml-org/gemma-4-31B-it-GGUF
 ```
-Then, access http://localhost:8080

 ---
+license: other
+tags:
+- gguf
+- quantized
 base_model:
 - google/gemma-4-31B-it
 ---
+# gemma-4-31B-it
+Run with https://llama.app
+```bash
+llama serve -hf ggml-org/gemma-4-31B-it-GGUF
 ```
+### Source models
+- https://huggingface.co/google/gemma-4-31B-it
+- https://huggingface.co/google/gemma-4-31B-it-assistant
+- https://huggingface.co/google/gemma-4-31B-it-qat-q4_0-unquantized
+- https://huggingface.co/google/gemma-4-31B-it-qat-q4_0-unquantized-assistant
+- https://huggingface.co/z-lab/gemma-4-31B-it-DFlash
+### TODOs
+- add info

+version https://git-lfs.github.com/spec/v1
+oid sha256:5ab00fcb6e94c8b86af3013d083fc7fc5056c23c69c38954e574b676e9a09517
+size 3087852704

+version https://git-lfs.github.com/spec/v1
+oid sha256:c0786f1df56ddcdfa3be1b5b9ef85fe2a84e4728f0fc764c82e84fd73f9dd777
+size 1647944864

+version https://git-lfs.github.com/spec/v1
+oid sha256:5b2c106a691fa0d6df5f3b8cfa43b4b3f2a3d2aa3ebbdeb303b459df2f1fd352
+size 61413189856

+version https://git-lfs.github.com/spec/v1
+oid sha256:031dc1c5fa9c5a0abbf3c39c5173fb2af65f5ac2dc2a090268561d3c72dcd834
+size 17992313088

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1105410e64013afa6fcfcd1620b30277025e61d51dbd0a253f41d7b96ae39fff
-size 32635674400

 version https://git-lfs.github.com/spec/v1
+oid sha256:fcd52cebacb165a98df5abe6fb70dbf076835f4a06e064ffb33dd739b8835c9c
+size 32635676896

+version https://git-lfs.github.com/spec/v1
+oid sha256:0e1e4f24cba407a7b91aab0a4175f923dcb075455edd216577270fdffb24658b
+size 1200726368

 version https://git-lfs.github.com/spec/v1
+oid sha256:8872f1dd7ba6a750a039c04b45812511f4ecf004e229420cea58c8049a970fb6
+size 809541728

+version https://git-lfs.github.com/spec/v1
+oid sha256:c8e9521c8894fe18cf11549b79fbd59fbfece7f017f95e0f7936d1752cf15463
+size 954843264

+version https://git-lfs.github.com/spec/v1
+oid sha256:f8f1b8c89b72da2b7391d6fe29d26dd373efe9624a3d5b3f0e99e62579b12c08
+size 279956160

	@@ -0,0 +1,5 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6b52ab20af503aee320dc09e93f886133b18d89ffc9075c7d9dcaf681e20b375
+size 514687104