← All episodes
EPISODE 341

Gemma 4 brings thinking mode to laptops

Learning GenAI via SOTA Papers · August 1, 2026 · 24 min

This report details Gemma 4, introducing a native thinking mode that allows models to generate structured reasoning traces before responding to queries. It also presents novel compute-efficient Mixture-of-Experts architectures and a unified, encoder-free framework for multimodal ingestion, establishing key primitives for next-generation open models.

Short on time? Watch the video overview of this paper.

Listen on: Spotify · Apple Podcasts · Amazon Music · YouTube

Follow the show: YouTube · Medium · X · LinkedIn · Bluesky · Threads · Instagram · TikTok · Facebook · Telegram