Gemma 4 E2B IT

Ultra-small model optimized for minimal cost and maximum speed.

• Ultra Efficient. ~2B-scale model with very low compute and memory requirements.

• Basic Capabilities. Handles simple chat, classification, and formatting tasks - not built for deep reasoning.

• Edge Friendly. Can run on very limited hardware while maintaining acceptable output quality.

• Apache 2.0 License. Fully open and permissive for commercial use.

Why pick it for Norman AI?

Gemma 4 E2B IT is the cheapest option for simple tasks. Use it for high-volume, low-complexity workloads where cost and latency matter more than intelligence.

messages = [
    {"role": "system", "content": "You are a helpful AI assistant."},
    {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"},
    {"role": "assistant",
     "content": "Sure! Here are some ways to eat bananas and dragonfruits together"},
    {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"},
]

response = await norman.invoke(
    {
        "model_name": "gemma-4-e2b-it",
        "inputs": [
            {
                "display_title": "Prompt",
                "data": messages
            }
        ]
    }
)

messages = [
    {"role": "system", "content": "You are a helpful AI assistant."},
    {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"},
    {"role": "assistant",
     "content": "Sure! Here are some ways to eat bananas and dragonfruits together"},
    {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"},
]

response = await norman.invoke(
    {
        "model_name": "gemma-4-e2b-it",
        "inputs": [
            {
                "display_title": "Prompt",
                "data": messages
            }
        ]
    }
)

messages = [
    {"role": "system", "content": "You are a helpful AI assistant."},
    {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"},
    {"role": "assistant",
     "content": "Sure! Here are some ways to eat bananas and dragonfruits together"},
    {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"},
]

response = await norman.invoke(
    {
        "model_name": "gemma-4-e2b-it",
        "inputs": [
            {
                "display_title": "Prompt",
                "data": messages
            }
        ]
    }
)

messages = [
    {"role": "system", "content": "You are a helpful AI assistant."},
    {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"},
    {"role": "assistant",
     "content": "Sure! Here are some ways to eat bananas and dragonfruits together"},
    {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"},
]

response = await norman.invoke(
    {
        "model_name": "gemma-4-e2b-it",
        "inputs": [
            {
                "display_title": "Prompt",
                "data": messages
            }
        ]
    }
)