Google Releases Gemma 3 270M for On-Device AI

Google DeepMind has expanded its Gemma 3 family with a new, ultra-compact model: Gemma 3 270M. This latest release focuses on bringing capable language model performance to resource-constrained environments where computational power and memory are limited.

At just 270 million parameters, the model is significantly smaller than its multi-billion parameter counterparts. This small footprint makes it a strong candidate for running directly on devices like smartphones, laptops, and web browsers, enabling applications that can operate offline and without relying on cloud-based APIs.

Despite its size, Gemma 3 270M features a modern architecture and a substantial 32,768-token context window. Google positions the model as an ideal, cost-effective base for developers and researchers looking to experiment with fine-tuning for specialized tasks.

The model is available now on Hugging Face under the custom Gemma license. This release continues Google's strategy of providing a range of open models to cater to different scales of development, from large-scale research to local, privacy-preserving applications.