@osanseviero: Super excited to introduce Gemma 4 12B! - Multimodal: audio, image, video, and text input - Novel architecture: we remo…

X AI KOLs Timeline Models

Summary

Introducing Gemma 4 12B, a multimodal model supporting audio, image, video, and text input with a novel unified architecture and a new MacOS desktop app powered by LiteRT.

Super excited to introduce Gemma 4 12B! 💎 - Multimodal: audio, image, video, and text input - Novel architecture: we removed the multimodal encoders for a unified, streamlined arch - New MacOS desktop app powered by LiteRT - MTP support Excited to see what you build with it! https://t.co/De5id2XQfz
Original Article
View Cached Full Text

Cached at: 06/03/26, 05:52 PM

Super excited to introduce Gemma 4 12B! 💎

  • Multimodal: audio, image, video, and text input
  • Novel architecture: we removed the multimodal encoders for a unified, streamlined arch
  • New MacOS desktop app powered by LiteRT
  • MTP support

Excited to see what you build with it! https://t.co/De5id2XQfz

Similar Articles

Introducing Gemma 4 12B: a unified, encoder-free multimodal model

Google DeepMind Blog

Google DeepMind announces Gemma 4 12B, a novel encoder-free multimodal AI model that integrates vision and audio directly into the LLM backbone, delivering advanced reasoning and agentic capabilities on laptops with 16GB of RAM, released under Apache 2.0 license.