Load the model to start
It downloads 510 MB from Hugging Face once, then your browser keeps it. Everything runs on your GPU, so nothing you type leaves this page.
Switching the effort mid-chat isn't recommended. This chat is on . to use the new one.
Runs Minico-M1-1105-ONNX (8-bit) with Transformers.js. Built on LFM2.5-350M by Liquid AI, under the LFM Open License v1.0. It is a small model and gets facts wrong; check anything that matters.