{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"AI News Today | Julian Goldie Podcast","title":"Google's NEW Gemma 4 Just Changed AI Forever...","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/2fe251d1\"></iframe>","width":"100%","height":180,"duration":715,"description":"Gemma 4 12B: Google's New Private & Free Local AI Model\nDiscover Google's latest Gemma 4 12B model, a lightweight yet powerful multimodal AI you can run privately on your own laptop. We break down its Mixture of Experts architecture, impressive benchmarks, and how to set it up for your AI agents for free.\n00:00 - Intro to Google Gemma 4 12B\n01:03 - Multimodal Intelligence Explained\n02:24 - Hardware Requirements & Size\n03:44 - Mixture of Experts Architecture\n04:39 - 256K Context & Privacy Benefits\n05:42 - Performance Benchmarks vs Larger Models\n07:04 - How to Run Gemma 4 Locally\n09:12 - Free API & Agent Integration\n10:31 - Recap: Is Gemma 4 the New Standard?","thumbnail_url":"https://img.transistorcdn.com/Tp0JSUlyiAe2ran44b13cjk4ImQYS1QEMKCAa9Q7go0/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9lNTYz/NGQxMTU2ZTM1MzU5/MDNiYjcwZjJmYTY5/ODJmOS5qcGc.webp","thumbnail_width":300,"thumbnail_height":300}