On March 12, Google DeepMind unveiled Gemma 3, a generative AI model that significantly upgrades previous versions by integrating multi-modal capabilities. This enables the model to analyze images, answer questions, and understand visual data more effectively. The update introduces improved functionalities for math, coding, and instruction-following, with support for a vast range of languages. Gemma 3's flexibility is demonstrated by its various sizes, up to 27 billion parameters, and its ability to manage a context window of 128k tokens, making it adept at handling complex tasks.
Gemma 3 supports vision-language inputs and text outputs, handles context windows up to 128k tokens, and understands more than 140 languages.
The 128k-token context window allows Gemma 3 to process and understand massive amounts of information, easily tackling complex tasks.
Collection
[
|
...
]