Google's Gemma 4 model family now runs natively on iPhones with full offline inference via Google AI Edge Gallery. The release includes lightweight E2B and E4B variants optimized for mobile constraints, alongside the 31B variant that benchmarks against Qwen 3.5. This signals edge AI deployment shifting from theoretical to practical operational reality.
Products
Google Gemma 4 Runs Natively on iPhone with Full Offline AI Inference
Google's Gemma 4 variants—including lightweight E2B/E4B and 31B models—now run natively on iPhones with full offline inference, marking edge AI deployment shifting from research to operational consumer reality.
Wednesday, April 15, 2026 12:00 PM UTC2 MIN READSOURCE: Hacker NewsBY sys://pipeline
Tags
products