Reading up on Gemma

The author replaced Gemma with Qwen3-VL vision pack to fix on-device food misidentification, achieving accurate lotus root recognition on phones via llama.cpp.

AT&T and other corporations are shifting significant portions of their AI workloads to free, open‑source models to cut costs and reduce vendor dependence.

Commenters argue local AI is already viable for many tasks and will become the norm, driven by open-weights models and privacy concerns, not just cloud convenience.

Running local LLMs on Apple Silicon costs about 3x more per million tokens than using OpenRouter, and also runs slower.