Consider this larger vision and writing model when your computer has room beyond the compact options. Start with one image or a short document excerpt.
Where it works well
- Image understanding and text generation in one model.
- An intermediate size between Gemma 3 4B and 27B.
- Support for writing and summarizing across multiple languages.
Common use cases
- Draft a caption and description for a presentation image.
- Ask focused questions about a clear chart screenshot.
- Restructure a report excerpt for a different audience.
Know its limits
- Check chart values and quoted text against the image; visual answers can be inaccurate.
- The advertised long context does not mean your computer has memory to use all of it.
- A smaller model may be more comfortable if you keep many apps open.
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 8.2 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.