A compact Gemma4 option for experimenting with local text and image questions. The E label describes effective parameters; the complete download is larger than a simple 2B label suggests.
Where it works well
- Designed for smaller devices.
- Image and text input in supported apps.
- Configurable thinking support.
Common use cases
- Describe a photo for a journal entry.
- Simplify a short piece of writing.
- Ask a focused question about a screenshot.
Know its limits
- Effective parameter count does not equal total model size; check the download and RAM estimate.
- Small visual details may be missed. Audio features depend on runtime and app support.
Run it on your computer
Start with a compressed download and a short conversation. Our estimate is about 12 GB of total RAM or Mac unified memory, with room for the operating system. The listed 4.6–7.5 GB download is the model file, not its full running memory use.
Check the model’s supported runtime and hardware before loading it. System RAM on a PC and unified memory on a Mac are different from dedicated NVIDIA VRAM. A memory match doesn’t guarantee compatibility or speed. Choose a smaller model if responses are too slow.
Use a desktop app that supports the listed model format, such as LM Studio or Ollama. Download the exact local variant, load it in Chat, and start with one small task. Model downloads need internet; local chat can work offline once the model is downloaded.
Official model information
Model capabilities checked October 2026. The use cases above are practical starting suggestions, not performance guarantees.