WebLLM Chat (An LLM Running in Your Browser)
A chat service that runs a language model directly inside your browser. Unlike other chatbots, your conversation is processed on your own computer instead of being sent to a server. The interface supports Korean.
How to try it
Type a question in the box at the bottom and press send to get a reply; tap the model name above the box (for example Llama-3.2-1B-Instruct) to switch models. Use 'New Chat' on the left to start over, and 'Settings' to adjust details. The first run downloads a model file of 800MB or more, so it takes a while, and it requires a recent Chrome or Edge with WebGPU — it will not run on phones or older browsers.