Marin 535B Training Starts with Full Transparency on FLOPs and Configs
_ScottCondron · x · 2026-08-23
The Marin initiative has launched its largest open model training run to date: 535B parameters (Active 23B). The project is notable for extreme transparency:
- Compute Stack: 11 x GB200 NVL72 systems.
- Voyage Plan: 80% pretraining + 20% midtraining on 18.75T tokens, expected to last 3 months, totaling 2.7e24 FLOPs.
- Transparency: Visualizations of domain mixture ratios, sampled documents, live training loss, configs, and scaling laws are publicly accessible.
Prior to the hero run, the team trained a 4-rung scaling ladder (1.6B to 27.7B) to debug issues and forecast performance.
More from Infra
- Fluidstack hires Electrical Engineer for Modular R&D to build frontier AI infrastructure — MxMnr · 2026-10-16
- Jensen Huang joins BG2 podcast: does AI revenue justify capex, '27 bottlenecks — elonmusk · 2026-10-16
- Mistral's on-device infra rack revealed: DGX Spark, Mac Studio and more — gregmushen · 2026-10-16
- NVIDIA and Sweden's Wallenberg launch Sferical One, a shared AI supercomputer — nvidia · 2026-10-16
- Next infra frontier: self-evolving systems that adapt and self-verify — _shreya_s · 2026-10-16
- Xiaomi's MiMo RL dashboard reveals $3.47M spent on just 30 training steps — bycloud · 2026-10-16