Today we’re introducing Gemma 4 12B — our latest open model that brings advanced agentic reasoning, vision and audio directly to your laptop.
It delivers performance nearing our larger Gemma models with a much smaller total memory footprint, while being small enough to run locally with just 16GB of VRAM. It’s open and accessible for everyone to use under a permissive Apache 2.0 license.
This is all made possible by our new, unified architecture that removes separate multimodal encoders. Here’s how we did it 🧵
Meet Gemma 4 12B!
A unified, encoder-free multimodal model designed to bring high-performance intelligence directly to your laptop, and released under an Apache 2.0 license.
Bridging the gap between edge efficiency and advanced reasoning. Here is what’s new with Gemma 4 12B: 👇
@adyshimony@googlegemma In the config menu, there’s a switch at the bottom, Enable speculative decoding. Remember to update the model by clicking on the update icon on the model selection screen.
Gemma 4 up to 3x faster, directly in your phone! 🚀
Check out the difference Speculative Decoding makes! Multi-Token Prediction (MTP) is supercharging inference speeds for Gemma 4.
Super excited to announce the Gemma 4 On-Device Meetup in Bangalore! 🇮🇳💎
We're bringing the community together for an evening of hands-on building. Join us to build local agentic workflows and push the limits of on-device ML with Gemma 4 and LiteRT-LM.
Bring your laptop and let's build together. Secure your spot by RSVPing here:
https://t.co/Ark7npmaOX
Lots of love for Gemma 4! Team just told me it’s already had 10M+ downloads since last week’s launch. Gemma models have now been downloaded 500M+ times! Excited to see what you all are creating 👀
Gemma 4 can run on phones without an internet connection! 🤯
It can perform local agentic tasks, such as logging and analyzing trends. When connected, it can also make API calls.
Want to try it yourself? Get the Google AI Edge App on iOS or Android. (🔊 Sound on for the demo!)
AI Edge Gallery allows you to build your own agentic, multimodal interactions with our Gemma 4 on-device mobile models.
Create your own skills and have a try now 👇
This Changes Everything. Google Edge Gallery is a MUST for every smartphone, this is a straight up lifesaver.
Imagine you’re on a trip, no internet, completely different language, trying to eat something but the packaging makes zero sense… and your phone just handles it instantly.
And that’s just a SMALL example of on-device AI running locally without internet… this is insane.
Gemma 4 running on my iPhone works without internet, is blazing fast and can translate Japanese from a pill bottle.
Local AI models running on a phone feels like magic.
@osanseviero Love the piano skill! I had a lot of fun building the AR Translation skill (powered by #MediaPipe). Gemma4 + #EdgeGallery is a brilliant combination, can't wait to see all the cool stuff that will get built out!
Thanks for following us!
We're excited to see what you all build with Gemma 4!
In case you missed it, you can find all our checkpoints, with an Apache 2.0 License, on Hugging Face:
As part of the Gemma 4 release, we're launching Agent Skills: an Android app experience where you can import different skills and have Gemma 4 E2B reason and use the skills!
Running entirely in the phone, available in the Google PlayStore. Try it now!