A mixture-of-experts Gemma4 variant for a well-equipped desktop or Mac. Its active parameter count affects computation, while the whole model still needs memory.
Where it works well
- Mixture-of-experts architecture.
- Text and image input.
- Reasoning and coding tasks in the Gemma4 family.
Common use cases
- Review a slide and suggest a clearer structure.
- Compare two supplied implementations.
- Create a detailed outline from reference notes.
Know its limits
- Around 4B active parameters does not make this a 4B-sized download.
- The 16–19 GB download still needs context and OS memory; GPU speed depends on VRAM fit.
Run it on your computer
Start with a compressed download and a short conversation. Our estimate is about 48 GB of total RAM or Mac unified memory, with room for the operating system. The listed 16–19 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.