Gemma 4: Byte for byte, the most capable open models
DeepMind launches Gemma 4, its most capable open AI models.
DeepMind has unveiled Gemma 4, its most advanced open AI models, engineered for complex reasoning and agentic workflows. With a focus on intelligence-per-parameter, Gemma 4 offers four model sizes, including the 31B Dense, which ranks as the third-best open model globally. Released under an Apache 2.0 license, these models are designed for accessibility and efficiency across a wide range of hardware, empowering developers to create innovative applications.
Key Takeaways
- 1.
Gemma 4 is available in four sizes, including 31B Dense, which ranks as the #3 open model globally.
- 2.
The models support over 140 languages, enhancing accessibility for global developers.
- 3.
Gemma 4 is released under an Apache 2.0 license, promoting open-source flexibility.
Get your personalized feed
Trace groups the biggest stories, videos, and discussions into one feed so you can stay current without scanning ten tabs.
Try Trace free