A larger text model for a desktop or Mac with memory to spare. Try it for detailed drafts and problems that require keeping several constraints in view.
Where it works well
- Writing, coding, and reasoning in a single local model.
- A middle size before moving to the much larger 32B download.
- Structured conversations that combine instructions and supplied reference text.
Common use cases
- Review a project proposal against a checklist.
- Explain tradeoffs between two small code implementations.
- Turn research notes into an outline with open questions.
Know its limits
- The 9.3 GB download does not include memory needed by the OS or chat context.
- Reasoning can take longer on a CPU or when the model cannot fit in GPU memory.
- It can invent references or overlook a constraint; check the original material.
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 9.3 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.