Chrome's Hidden 4GB AI Download Exposes a Consent Problem
Google Chrome silently installs a 4GB Gemini Nano model file on users' devices, with storage requirements buried far from where users enable the features.
#on-device AI
Bonsai 1.7B Hits 442 Tokens Per Second on M4 Max: Ternary Weight Efficiency in Practice
A ternary-weight 1.7B model achieves 442 T/s on Apple M4 Max, demonstrating how ultra-compact weight encoding translates to real-world on-device inference speed.