# Berkeley Lab runs Meta's open-weight vision models on 300 graphics processors to cut beamline image analysis from a month to 15 minutes

The Department of Energy's SYNAPS-I project uses Segment Anything 3 and DINOv3 across five national laboratories, with the models running on the operator's own infrastructure.

- Published: 2026-10-27T06:18:03.036Z
- Canonical: https://polylog.news/ai/2026-10-27/berkeley-lab-runs-meta-s-open-weight-vision-models-on-300-gr
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Meta AI](https://ai.meta.com/blog/genesis-mission-lawrence-berkeley-national-laboratory-segment-anything-dino/), [Meta AI](https://ai.meta.com/blog/assistive-robotics-university-of-pittsburgh-sam-dino/)

Lawrence Berkeley National Laboratory is running Meta's open-weight perception models inside a Department of Energy science pipeline. The project, described by Meta, is called SYNAPS-I and is led by Berkeley Lab with Argonne, Brookhaven, Oa…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-10-27/berkeley-lab-runs-meta-s-open-weight-vision-models-on-300-gr (subscription information: https://polylog.news/pricing).