← Glossary Model
Gemma 4
Google's open model that you can download and run on your own computer.
Gemma 4 is an open-weight model from Google, a smaller cousin of the flagship Gemini models that anyone can download and run on their own hardware. Where Gemini is offered as a cloud service, Gemma is meant to be used locally.
That makes it a favourite for people who want AI that keeps data on their own machine, and it runs well through tools like Ollama. Improvements to how such models use Apple’s chips, for instance, have made Gemma dramatically faster on Mac computers with no downside.
Gemma is part of a wider movement of capable open models that give individuals and small businesses a private, low-cost alternative to cloud-only AI.
Mentioned in
-
Google's Free Models Passed a Billion Downloads. Some of Them Are Running in Orbit
-
The Most Valuable AI Skill Is Not Prompting. It Is Verification.
-
Nvidia's New Free Model Is Not the Smartest. It Is Just Very, Very Fast
-
Google Turned a Finished Model Into a Much Faster One, and Published the Recipe
-
We Ran a Local AI Model on a Six Year Old Budget Laptop Chip. Here Is Exactly What It Could Do.
-
Mira Murati's New Lab Ships Its First Model, and It's Built to Be Customized
-
Where the Network Ends, Small AI Begins: Tiny Models Are Saving Lives Offline
-
Free Speed Boost: Ollama Makes Local AI Up to 90% Faster on Macs