Marin begins pretraining Marin 535B-A23B, a mixture-of-experts model

In a launch note dated September 3, 2026, first published on the Open Athena blog and mirrored by Marin, Marin said it had started pretraining Marin 535B-A23B a couple of weeks earlier. The note describes a mixture-of-experts model with 535 billion total parameters and 23 billion active, planned to pretrain for about three months on 18 trillion tokens, and says the team ported its infrastructure and training stack from Google TPUs on GCP to NVIDIA GPUs on CoreWeave before launch, with post-training to follow. It says the entire run, including architecture, data, and predicted loss, is documented on GitHub; it does not give a date or license for releasing the model's weights.1

USASI. (2026, October 13). Marin begins pretraining Marin 535B-A23B, a mixture-of-experts model. United States of America Superintelligence. https://unitedstatesofamericasuperintelligence.com/news/marin-begins-pretraining-535b-a23b-model/

@misc{usasi_news_marin_begins_pretraining_535b_a23b_model,
  author = {{USASI}},
  title = {Marin begins pretraining Marin 535B-A23B, a mixture-of-experts model},
  year = {2026},
  month = oct,
  howpublished = {\url{https://unitedstatesofamericasuperintelligence.com/news/marin-begins-pretraining-535b-a23b-model/}},
  note = {United States of America Superintelligence. Last updated 2026-10-13}
}