Lightning is a 30B-total, 3B-active model. Use it in local chat for planning and extraction, or in compatible apps for tool use.
Where it works well
- Structured instructions and reasoning.
- Tool-oriented assistant tasks.
- Text extraction and summaries.
Common use cases
- Turn a project brief into ordered tasks.
- Extract structured fields from notes.
- Explain a code snippet and suggest checks.
Know its limits
- Tool calls need a compatible app and permissions; the model alone cannot manage email or files.
- The 25 GB default download needs more than 25 GB of system memory during use.
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 25 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.