Gemma 3 270M

Training compute

9.7×10²¹ FLOP

Parameters

270M

Published

Aug 14, 2025

Gemma 3 270M is an AI model developed by Google DeepMind (United States), first published in August 2025. It works in the language domain, on tasks such as language modeling/generation and question answering.

Training it took an estimated 9.7×10²¹ FLOP of compute (estimation method: operation counting). The model has 270,000,000 parameters. It was trained on roughly 6T datapoints.

Access: Open weights (restricted use). Its weights are openly available. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Google DeepMind
Country of organization: United States
Domain: Language
Task: Language modeling/generation, Question answering
Training compute: 9.7×10²¹ FLOP
Compute estimation method: Operation counting
Parameters: 270,000,000
Dataset size: 6T
Model accessibility: Open weights (restricted use)
Open weights: Yes
Epoch confidence: Confident