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.
More from Models
- Rumor: DeepSeek-V4 Performance to Rival Claude Opus 4.8 with Disruptive Pricing — teortaxesTex · 2026-07-31
- Deep20Bench tests LLM strategy via 'Twenty Questions': Opus 5 and Kimi K3 lead the pack — wauwau0977 · 2026-07-31
- DeepSeek-V4-Flash surpasses V4-Pro-Preview in latest benchmarks — Outside-Risk-8912 · 2026-07-31
- DeepSeek-V4-Flash API Public Beta: Agent Capabilities Boosted Purely via Post-Training — 新智元 · 2026-07-31
- DeepSeek-V4-Flash-0731 far surpasses DeepSeek-V4-Pro-Preview in benchmarks — SnooBunnies8392 · 2026-07-31
- DeepSeek's Price War Sparks Hype for DeepSeek 4 Pro — kimmonismus · 2026-07-31