Gemma 4

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "google/gemma-4-27b-it",
    device_map="auto",
    torch_dtype="auto"
)
tokenizer = AutoTokenizer.from_pretrained("google/gemma-4-27b-it")

messages = [
    {"role": "user", "content": "Explain quantum computing in simple terms."}
]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt")
outputs = model.generate(inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0]))

# Install and run with Ollama
ollama run gemma4:27b

# Or pull first, then run
ollama pull gemma4:27b
ollama run gemma4:27b

# Use with API
curl http://localhost:11434/api/generate -d '{
  "model": "gemma4:27b",
  "prompt": "Explain quantum computing in simple terms."
}'

# No installation needed!
# 1. Go to https://aistudio.google.com/
# 2. Select Gemma 4 model
# 3. Start prompting

# Or use the API:
import google.generativeai as genai

genai.configure(api_key="YOUR_API_KEY")
model = genai.GenerativeModel("gemma-4-27b-it")

response = model.generate_content(
    "Explain quantum computing in simple terms."
)
print(response.text)