Consider the larger gpt-oss model only after trying 20B. This is a real local download for a high-memory desktop or Mac, with much greater hardware demands.
Where it works well
- Detailed reasoning with supplied context.
- Planning and coding-oriented text tasks.
- Adjustable reasoning effort in supported runtimes.
Common use cases
- Review a technical plan for gaps.
- Compare design alternatives.
- Analyze a difficult code excerpt.
Know its limits
- 65 GB is the download, not the full runtime requirement; context and the OS need additional memory.
- Enough RAM does not guarantee usable speed or a fit in GPU memory.
Run it on your computer
Start with a compressed download and a short conversation. Our estimate is about 96 GB of total RAM or Mac unified memory, with room for the operating system. The listed 65 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.