A larger mixture-of-experts choice for a personal machine with substantial memory. Compare it with a smaller model on a task you actually repeat.
Where it works well
- Text and image input.
- A mixture-of-experts architecture.
- Writing, reasoning, and code in one local model.
Common use cases
- Review a draft for conflicting requirements.
- Compare implementation options using supplied code.
- Explain a diagram and its written description.
Know its limits
- All weights still need memory, even though only some experts activate per token.
- A 22 GB download can be slow when split between GPU and CPU. Large context needs more memory.
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 22 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.