Gemma 4 31B

pip install -U transformers

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

pipe = pipeline("image-text-to-text", model="google/gemma-4-31B")

pip install -U transformers

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("google/gemma-4-31B")
model = AutoModelForMultimodalLM.from_pretrained("google/gemma-4-31B", device_map="auto")

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-GGUF:BF16

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

winget install llama.cpp

# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ggml-org/gemma-4-31B-GGUF:BF16

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

# 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-GGUF:BF16

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

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-GGUF:BF16

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

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

ollama run hf.co/ggml-org/gemma-4-31B-GGUF:BF16

npx -y node-llama-cpp chat hf:ggml-org/gemma-4-31B-GGUF:BF16

npx -y node-llama-cpp inspect estimate hf:ggml-org/gemma-4-31B-GGUF:BF16

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

curl https://localai.io/install.sh | sh

# Load and run the model:
local-ai run huggingface://ggml-org/gemma-4-31B-GGUF/{{GGUF_FILE}}

# Pull the image:
docker pull localai/localai:latest-cpu

# Load and run the model:
docker run -p 8080:8080 --name localai -v $PWD/models:/build/models localai/localai:latest-cpu huggingface://ggml-org/gemma-4-31B-GGUF/{{GGUF_FILE}}

# Download Lemonade from https://lemonade-server.ai/

lemonade pull ggml-org/gemma-4-31B-GGUF:BF16

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

lemonade list