A coding-focused 80B mixture-of-experts model supplied here in its local Q4_K_M version. It suits a high-memory desktop or Mac rather than a typical laptop.
Where it works well
- Designed for coding and development tools.
- Tool calling through compatible coding apps.
- Non-thinking output without a separate reasoning stream.
Common use cases
- Plan a small refactor across supplied files.
- Suggest a patch for a reproducible bug.
- Generate tests for a specific edge case.
Know its limits
- Its 3B active parameters do not shrink the 52 GB weight download.
- File access and test execution require configured app tools; the full advertised context needs much more 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 52 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.