Running LLMs on your iPhone: 40 tok/s Gemma 4 with MLX — Adrien Grondin, Locally AI

About this video

Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidence

Demonstrates running Gemma 4 on iPhone hardware with specific performance metrics. Teaches practical deployment and optimization for edge devices.

A 11-minute video from AI Engineer: “Running LLMs on your iPhone: 40 tok/s Gemma 4 with MLX — Adrien Grondin, Locally AI”.

Video by AI Engineer, played through YouTube's embedded player.

Part of Open Models @ AI Engineer