Released October 13, 2026, this larger Liquid AI model reasons before answering. Keep the first task small while checking speed on your computer.
Where it works well
- Reasoning through constrained tasks.
- Multilingual instruction following.
- Tool-oriented workflows in compatible apps.
Common use cases
- Compare plans against a list of constraints.
- Explain a small coding problem.
- Build a structured summary from your notes.
Know its limits
- It always reasons, so simple requests can take longer.
- Its 2B active parameters do not mean 2B worth of memory; all weights must fit.
Run it on your computer
Start with a compressed download and a short conversation. Our estimate is about 32 GB of total RAM or Mac unified memory, with room for the operating system. The listed 15 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.