Google Releases Gemma 3 270M for On-Device AI
The new ultra-compact model from DeepMind is designed for efficient performance in resource-constrained environments like mobile and web.
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.
Sources
- Visit
google/gemma-3-270m
Hugging Face
More from Google DeepMind
All Google DeepMind releases →
EmbeddingGemma 2 Expands to Any Modality
Google DeepMind's compact embedding model now spans text, vision, audio, and video in a single vector space.
Google DeepMind's Gemma 4 Goes Multimodal and MoE
The new open-weights family adds a mixture-of-experts design, encoder-free multimodal inputs, and an optional thinking mode.
Google DeepMind Releases TabFM for Tabular Data
A new foundation model brings zero-shot, in-context learning to classification and regression on structured tables.
More in Text / LLM
All Text / LLM →IBM's Granite Switch Treats Models Like Software
A new Apache-2.0 release reframes enterprise LLMs as components you can swap and update in place.
Mistral Large 4 Arrives as a 1T-Parameter MoE
The new flagship pairs a trillion total parameters with 52B active per token and adds vision alongside multilingual text.
Nanbeige 4.3 Arrives as a 33B Bilingual Model
A dense English–Chinese language model lands under Apache 2.0, aimed at teams that want permissive licensing at mid-size scale.
0 comments
No comments yet. Be the first to weigh in.