Google Releases Gemma 3 Household of Open-Supply AI Fashions, Can Run on a Single GPU

Google launched the Gemma 3 household of synthetic intelligence (AI) fashions on Wednesday. Successor to the Gemma 2 sequence, which was launched in August 2024, the brand new open-source fashions arrive with textual content and visible reasoning capabilities. The Mountain View-based tech big stated these fashions provide help for greater than 35 languages and may be fine-tuned to supply extra help for 140 languages. Notably, the tech big claimed that these fashions are optimised to run on a single GPU or Google’s Tensor processing unit (TPU).

Google Releases Gemma 3 Collection AI Fashions

In a weblog put up, the tech big detailed the brand new small language fashions (SLMs), highlighting that these had been constructed utilizing the identical know-how as the corporate’s flagship Gemini 2.0 fashions. The Gemma sequence is understood for being open-source and providing on-device efficiency. Google revealed that to this point, the Gemma fashions have been downloaded greater than 100 million occasions and have been used to create greater than 60,000 variants.

The tech big claimed that Gemma outperforms Meta’s Llama-405B, DeepSeek-V3, OpenAI’s o3-mini AI fashions on the LMArena’s leaderboard. These fashions can be found in 4 sizes — 1B, 4B, 12B, and 27B parameters. They are often run on a single GPU or TPU, the corporate claimed.

Gemma 3 sequence gives superior textual content and visible reasoning capabilities, and might analyse photographs, textual content, and quick movies. The AI fashions provide a context window of 1,28,000 tokens. The fashions additionally provide operate calling help, which can permit builders to construct agentic capabilities within the apps and software program they create.

Google stated that the AI fashions had been developed utilizing cautious threat evaluation. The corporate claimed that it enforced inner security insurance policies through fine-tuning and benchmark evaluations. The fashions had been additionally examined utilizing extra succesful fashions. The mannequin displayed a low threat degree, the corporate claimed.

Along with Gemma 3 sequence, the corporate additionally launched ShieldGemma 2, a 4B parameter picture security checker, that ensures that the AI fashions don’t generate content material with harmful, sexually express, or violent content material. Builders have additionally been given the choice to additional customise ShieldGemma to reinforce the security parameters. Gemma 3 household of AI fashions may be downloaded through Google’s Hugging Face itemizing or on Kaggle.