Pico AI Server for MLX LLM VLM 17+

Lightning fast AI server for home and office. Built on MLX, powered by the latest R1 models. Now supports any chat client.

Lightning Fast. Complete Privacy. Effortless Setup.

Pico is the ideal LAN AI server for home and office use—designed for professionals and small teams. It offers key benefits:

• Pico AI Homelab includes over 300 state-of-the-art models such as:
• DeepSeek R1
• Meta Llama
• Microsoft Phi 4
• Qwen 2.5
• Sky T1
• Google Gemma 2
• Mistral
…And many more

• Compatible with your existing chat app, including:
• Open WebUI
• Apollo AI
• Bolt AI
• IntelliBar
• Msty
• Ollamac
• MindMac
• Enchanted
• Kerling
• LibreChat
• Hollama
• Ollama-SwiftUI
• Witsy
• Reactor AI
... And many more

• Fast Performance – Built for Apple Silicon and powered by Apple MLX, Pico delivers lightning-fast results to help you work efficiently.

• Completely Free – Since Pico processes everything locally on your computer, there’s no monthly subscription or API call cost.

• Easy Setup and Customization – No command line skills required. With a guided, one-click installation, even beginners can get started quickly, while power users enjoy flexible customization options.

• Total Privacy – All AI models run on your computer over your local network (LAN), keeping your data secure and private.

• Ollama Compatibility – Pico is compatible with the Ollama API, letting you easily integrate it with chat apps like Open WebUI, Ollamac, and MindMac for a smooth, efficient workflow.

• System Requirements – Pico requires an Apple Silicon machine (M1 or later). It runs with 16GB of memory as a minimum, though 32GB or more is recommended for optimal performance.

Try Pico—your fast, secure, and entirely free local AI server. Download it today