Musk Says 2.5T-Parameter Grok 4.8 Finishes Training This Week

Elon Musk says Grok 4.8 is a 2.5-trillion-parameter model trained on xAI's new C++ stack, finishing pretraining this week before entering reinforcement learning.

2026-09-14 ~ 2026-09-14 · 2 related posts

• Musk says 2.5T-parameter Grok 4.8, trained on new C++ stack, finishes training this week — inductionheads · 2026-09-14
• Elon: Grok 4.8 is a 2.5T parameter model, starts RL after training this week — ns123abc · 2026-09-14