Nativ enables local execution of Gemma 4 and Liquid AI models on Mac

Nativ provides a local inference tool for macOS that selects models based on hardware constraints. Supported models include Google's Gemma 4 (10.28 GB, 128K context), Cohere's North Mini Code (19.38 GB, 500K context), and Liquid AI's LFM2.5-VL 1.6B (3.20 GB, 128K context).