Gemini Nano-2

Parameters

3.3B

Published

Dec 19, 2023

Gemini Nano-2 is an AI model developed by Google DeepMind (United States), first published in December 2023. It works in the multimodal, language, vision and audio domain, on tasks such as chat, image captioning and speech recognition (asr).

Epoch AI has no training-compute estimate for this model. The model has 3,250,000,000 parameters. Training ran on Google TPU v5e.

Access: Unreleased. Its weights are not openly released. The reference paper has 633 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Google DeepMind
Country of organization: United States
Domain: Multimodal, Language, Vision, Audio
Task: Chat, Image captioning, Speech recognition (ASR)
Parameters: 3,250,000,000
Training hardware: Google TPU v5e
Model accessibility: Unreleased
Open weights: No
Citations: 633
Epoch confidence: Confident