Marin's open 535B-A23B model is 13% trained, funded by Huang Foundation
dlwh · x · 2026-09-04
Marin, the collaborative open-source project led by Percy Liang, is 13% through training its 535B-parameter, 23B-active model. The hero run was funded by the Jen-Hsun and Lori Huang Foundation, with compute provided by Coreweave. Community members praise Marin as one of the most collaborative open-source efforts, with Discord questions answered within minutes.
Related event: Stanford's Marin 535B-A23B Open Model Hits 13% of Training(2 posts)→
More from Infra
- Micron explores near-GPU NAND flash to run bigger LLMs — giveen · 2026-09-04
- HPE Delivers Strong Q3 on AI Server Demand, Raises FY2026 Outlook — mattwbaker · 2026-09-04
- All Chromium Browsers Hit by Hard-to-Reproduce Data Loss Bug, Devs Say — uwukko · 2026-09-04
- Hundreds protest Scotland's datacentre boom, demanding pause on 20+ proposed projects — nordicinst · 2026-09-04
- Built a Dual RTX 6000 Pro Rig for Local DeepSeek — Warns Against Influencer Build Hype — HankYeomans · 2026-09-04
- Inference engines are an underexamined attack surface, self-hosting ops warned — JeremyCMorgan · 2026-09-04