The June 2026 addition between the small edge models and the larger Gemma4 variants. It is intended for laptop use, with a practical middle-size download.
Where it works well
- A mid-size option within the current Gemma family.
- Multimodal model design with text and image use in Ollama.
- Writing, code, and reasoning tasks with supplied context.
Common use cases
- Review a report excerpt for clarity.
- Describe a chart with readable labels.
- Explain a small program using example inputs.
Know its limits
- Native model capabilities such as audio require support in your chosen app and runtime.
- The large supported context is a ceiling, not a promise that it fits in 24 GB of RAM.
Run it on your computer
Start with a compressed download and a short conversation. Our estimate is about 24 GB of total RAM or Mac unified memory, with room for the operating system. The listed 7.7–8.0 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.