22:27
2026-08-22
twitter.com
large-language-models
Follow live the open training of a 535B (23B activated) LLM
Marin 535B-A23B, a 535-billion-parameter mixture-of-experts large language model with 23 billion activated parameters, began open training this week on 18.75 trillion tokens across 11 NVIDIA GB200 NVL…