Your AI, on your own hardware.
IXL runs local models on your GPU and gives you a browser-based chat from anywhere. Your prompts never touch a third-party API.
Local & private
Runs on your own GPU via Ollama. Prompts stay on your machine.
Any model
Qwen, Llama, LFM, Mistral — anything Ollama supports.
Anywhere
Access from any browser via Cloudflare Tunnel.