Gemma 3n models are multimodal by design and available in two sizes that operate with as little as 2GB and 3GB of memory, Google said.

InfoWorld is a source of news, analysis, and commentary on technology trends, IT strategies, and business innovation. With a focus on enterprise technology and digital transformation, InfoWorld offers insights and guidance for IT decision-makers, software developers, and technology professionals. From  articles on cloud computing and cybersecurity to product reviews and industry trends, InfoWorld helps readers navigate the complexities of modern IT environments and make informed decisions to drive business success.

InfoWorld

Google has released Gemma 3n, a new AI model family designed for on-device applications with multimodal capabilities supporting image, audio, video, and text inputs. Available in two sizes (E2B and E4B), these models operate efficiently with just 2-3GB of memory while delivering performance comparable to larger models. Built on Gemini nano technology, Gemma 3n supports 140 languages for text and 35 for multimodal understanding, with the E4B version achieving over 1300 LMArena score as the first sub-10B parameter model to reach this benchmark.

Google releases Gemma 3n models for on-device AI