Google DeepMind Releases Gemma 4 12B: An Encoder-Free Multimodal Model with Native audio that runs on a 16 GB laptop

Chronological Source Flow
Back

AI Fusion Summary

Google DeepMind released Gemma 4 12B, an open-weights, encoder-free multimodal model under the Apache 2.0 license. It natively processes text, images, audio, and video, running locally on consumer or enterprise laptops with 16 GB of RAM.
Community Comments
Loading updates...
0