A text-only reasoning model released August 2025. The local 20B tag downloads to your computer; keep context short to leave memory for other apps.
Where it works well
- Multi-step reasoning tasks.
- Configurable reasoning effort in supported apps.
- Structured text and coding assistance.
Common use cases
- Compare options using facts you supply.
- Explain a code snippet.
- Turn requirements into an action plan.
Know its limits
- It cannot see images or browse independently in a plain local chat.
- Reasoning takes time, and a detailed answer can still be wrong.
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 14 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.