Choose your model
Switch between supported local language models to suit your conversation.
Your ideas, a private conversation.
Brainstorm, draft, and ask questions with language models that run on your device. Switch models and revisit saved chats and drafts.
Switch between supported local language models to suit your conversation.
Adjust model configuration and generation settings in the workspace.
Save chats, drafts and model settings on this device. Search, rename and reopen them anytime.
Choose a model and configuration.
Download the model files to your browser.
Create a chat and explore your ideas.
We’ll email you when LocalAI chatbot is ready.
General chat and text continuation locally in a WebGPU browser. Choose 3B for chat or 3B Base to continue a text prefix.
Ask questions, draft short text, and experiment with multilingual conversations using a compact chat model. Returns an assistant reply; complex reasoning and factual answers need review.
Ask questions, draft short text, or continue a conversation with a compact multilingual chat model. Returns an assistant reply; answers can be inaccurate and should be checked.
Chat with text or images locally using Qwen3.5.
Chat with text, images or WAV audio using the complete Gemma 4 E2B and E4B checkpoints on verified configurations.