Gemma 4 Edge
Gemma 4 Edge uses Gemma 4, a lightweight Google AI model that runs inside NappAI: it needs no account or key for any service. You can use it in two ways: as the model of an agent, by connecting its Model output to the agent’s Model input, or on its own, so that it answers the text that reaches its Input.
The first time it is used, the model is downloaded, so that run takes longer than the following ones.
When to use it
- Give an agent the model it uses to understand requests, decide which tools to use and answer.
- Write, summarise or classify texts inside a flow, without an agent.
- Build tests and prototypes without signing up for an AI service.
- Simple text tasks, such as classifying messages or pulling out one piece of data.
Configuration
In the Common tab:
| Field | What it does |
|---|---|
| Model variant | The size of the model. E2B is the lightest; E4B is more capable and uses a little more memory. Default: E2B. |
| Temperature | How varied the answers are: low values give steadier, more predictable answers; high values, more creative ones. Default: 0.1. |
| Connection | What to connect |
|---|---|
| Input | The text the model must answer when it works on its own, for example the message of a Chat Input or the result of a Prompt. |
Advanced options
In the Advanced tab:
| Field | What it does |
|---|---|
| System Message | General instructions for the model when it works on its own: its role, the tone, what to avoid. You can type them or connect them from another component. |
| Stream | Shows the answer in the chat while it is being written, instead of waiting until it is finished. It only has an effect in the chat. Default: off. |
| Top K and Top P | Other ways to control how varied the answer is. Temperature is usually enough. |
| Context window | How much text fits between the request and the answer, in tokens. Lower it if length errors appear. Default: 6144. |
| Enable thinking | The model thinks before answering, which helps with complex tasks. The reasoning appears in the answer between <think> tags. Default: off. |
| Thinking budget | How many tokens it can spend thinking when Enable thinking is on; 0 means no limit. Default: 1024. |
| Other options | Backend, Custom model path: fine-tuning settings for advanced users. Leave them as they are if you don’t need them. |
Batch processing
With the Batch Mode switch on, the component runs once for each item of the list you connect to Batch Input and returns all the results together as a list. Parallel Executions sets how many items are processed at the same time (1 to 5). Skip if Empty Batch Input skips the component when the list arrives empty, and Skip Branch if Empty Output stops the following components when the result is empty. More in Key concepts.
Output
| Output | What it contains |
|---|---|
| Model | The configured model. It sits at the top of the component. Connect it to the Model input of an agent or of any other component that asks for a model. |
| Text | The model’s answer to the text received in Input. Connect it, for example, to a Chat Output or to another component that works with text. |
The two ways of using it exclude each other: when you connect the Model output, the component hides Input and Text, because the model now works inside the other component; and if you connect Input, Model is hidden.
Example
The language school Idiomas Plus wants to sort the messages from its contact form into “enrolment”, “timetables” or “other” without signing up for a service. It connects a Prompt with the categories to the Input of Gemma 4 Edge and sends the Text output to the next step of the flow.
Good practices
- Use a low Temperature when you need exact answers, such as classifying or extracting data, and raise it for more creative texts.
- If you use the model with an agent, configure only the model here: the instructions and the tools are set in the agent.