# Scaling Marin's Open LLM Pretraining

- **When:** Tue, Nov 17, 2026, 6:00 PM PST – 8:00 PM PST
- **Where:** San Francisco
- **Price:** Free (approval required)
- **Organizer:** [Andy Konwinski](https://eventing.ing/organizers/orgz_1m77m40gtaar1q07vjtz4d), [David Hall](https://eventing.ing/organizers/orgz_1m77m40gv156sqz5zd19vc), [Joy Jing](https://eventing.ing/organizers/orgz_1m1k91sjh6ct3r5s0f2b21), [Open Athena](https://eventing.ing/organizers/orgz_1m77m40ha05vjnpc93nqtk), [Percy Liang](https://eventing.ing/organizers/orgz_1m77m40ha0392z44px99nn), [Will Held](https://eventing.ing/organizers/orgz_1m77m40hb0yv67q9d0y9v9)
- **Categories:** AI & ML
- **View on Luma:** https://luma.com/8rz1myft

Marin started as an academic project with one full-time researcher, training medium-sized language models on Google’s TPU Research Cloud. This month, the team finished pre-training a 535B-parameter mixture of experts model on 18T tokens, using GPUs from the Huang Foundation, in the largest live-streamed pre-training run to date.

This required scaling everything: compute, data, focus, and people. We ran thousands of smaller models to understand scaling, built systems for…

Source: Luma. Eventing indexes this event and links to the source for tickets and the full description.

Same event as JSON: https://api.eventing.ing/events/evnt_1m77m40nc4fpa53fhze6rq