Running Liquid AI Models On-Device with the Apollo iPhone App

Melvin Vivas · X post · 2026-08-11 · Open on X

Topics: LLM Fundamentals, AI Dev Tools & Productivity · Level: beginner

Summary

The creator tries Liquid AI's models directly on his iPhone through the Liquid Apollo app. It is a quick pointer for anyone who wants to try small on-device language models.

Key points

• Liquid AI's models can run locally on an iPhone.
• The Liquid Apollo app is the way to try them on-device.
• Small, efficient models make mobile and edge inference possible.

Resources mentioned

• Liquid AI (@liquidai) on X · website · x.com · free
  An AI company that builds efficient foundation models. The quoted post shows its PII handling working on Japanese text.
  Also in: Zero-Shot Prompt Routing with Liquid AI's LFM 2.5-Encoder-350M (Melvin Vivas on X · notes), Liquid AI LFM 2.5 Encoder: a CPU-friendly encoder model (Melvin Vivas on X · notes), Fine-tuning Liquid AI LFM2/LFM2.5 MoE models with the new Halo framework (Melvin Vivas on X · notes), Liquid AI's LFM2-Longevity models for aging-data analysis (Melvin Vivas on X · notes) and 19 more
• Liquid Apollo · tool · liquid.ai · free
  Liquid AI's mobile app for running its models on-device.

Try this

• Try Liquid AI models on your phone with the Liquid Apollo app.