Gemini V4 Rumored to Train on Tens of Trillions of Tokens for Multimodal

teortaxesTex · x · 2026-07-31

Tech blogger teortaxesTex expressed high expectations for the multimodal capabilities of Google's next-generation Gemini V4 model. He predicts Google will throw tens of trillions of tokens at its training.

He also noted that a V4-Flash-Vision model already exists, suggesting Google might be taking extra time to handle the complex OPD (Original Pre-training Data) alignment for mixed modalities to ensure a flawless multimodal experience.

Original post →

More from Models

Models channel →