Stanford Starts Fully Open Training of 535B-Parameter Marin Model

Stanford CRFM has begun training its Marin 535B-A23B model on 11 GB200 NVL72 clusters, using 18.75T tokens over about three months. The entire training process is fully open and transparent to the public.

2026-08-22 ~ 2026-08-22 · 2 related posts

• Marin 535B training starts with full open process and scaling ladder — ysu_nlp · 2026-08-22
• Stanford launches Marin 535B training with full open process — soumitrashukla9 · 2026-08-22