Image → Tools

Local AI Chat

Have a private conversation with a locally-running LLM. No data leaves your machine.

Loading models…
Start a conversation — type a message below.⌘ + Enter to send

How to local AI Chat

  1. Install Ollama from ollama.com and run: ollama pull llama3.1:8b
  2. Start the Ollama server: ollama serve
  3. Pick a model from the dropdown above the chat.
  4. Type your message and press Send or ⌘+Enter.

All conversations stay on your machine. The LLM runs locally via Ollama — nothing is uploaded.

Related tools

AI SummarizerAI RewriterAI Translator

Frequently asked questions

Is this chat private?

Yes — the LLM runs entirely on your machine. No messages are sent to any external server.

Which model should I start with?

llama3.1:8b is an excellent all-rounder (4.7 GB). For a lighter option try llama3.2:3b (2 GB).

Why is Ollama not showing models?

Make sure Ollama is running (ollama serve) and you have pulled at least one model (ollama pull llama3.2).

Can I use LM Studio instead of Ollama?

Yes — set LLM_BASE_URL=http://localhost:1234/v1 in your .env.local and restart the dev server.