Google introduces Gemma 4 12B, a unified, encoder-free open multimodal model that can run locally on devices with 16GB of VRAM or unified memory (Carl Franzen/VentureBeat)

<a href="https://venturebeat.com/technology/googles-new-open-source-gemma-4-12b-analyzes-audio-video-and-runs-entirely-locally-on-a-typical-16gb-enterprise-laptop"><img align="RIGHT" border="0" hspace="4" src="http://www.techmeme.com/260603/i58.jpg" vspace="4" /></a> <p><a href="https://www.techmeme.com/260603/p58#a260603p58" title="Techmeme permalink"><img height="12" src="http://www.techmeme.com/img/pml.png" style="border: none; padding: 0; margin: 0;" width="11" /></a> Carl Franzen / <a href="https://venturebeat.com/">VentureBeat</a>:<br /> <span style="font-size: 1.3em;"><b><a href="https://venturebeat.com/technology/googles-new-open-source-gemma-4-12b-analyzes-audio-video-and-runs-entirely-locally-on-a-typical-16gb-enterprise-laptop">Google introduces Gemma 4 12B, a unified, encoder-free open multimodal model that can run locally on devices with 16GB of VRAM or unified memory</a></b></span>&nbsp; &mdash;&nbsp; While many AI open source model providers are pursuing larger and more powerful models, Google is still giving attention to the smaller, more local side of the market.</p>