# How xAID uses Nebius AI Cloud

**0.86** macro F1 score on the five acute conditions most

As published on [nebius.com](https://nebius.com/customer-stories/xaid). Captured by usedby on 2026-10-17.

- Company: [xAID](https://www.usedby.ai/companies/xaid.md)
- Tool: [Nebius AI Cloud](https://www.usedby.ai/tools/nebius.md)

## What the story says

xAID trains a large 3D transformer foundation model for AI-assisted medical imaging on Nebius AI Cloud, using chest and abdominal CT scans. Training runs on H100 GPUs and last several days per cycle, and the company relies on the platform for uninterrupted compute and MLOps support.

Summary written by usedby from the source page, in English. The figures are those of Nebius AI Cloud and xAID, not ours.

> With five days per epoch training on noisy clinical data, xAID relied on Nebius AI Cloud for consistent, high-performance computing, eliminating the risk of unexpected interruptions or infrastructure bottlenecks.

- **70-90%**: “GPU utilization can fluctuate, but xAID’s strategy kept it within a 70-90% range to make every GPU hour count.”

## What usedby checked

We compared the story with its live page on 2026-10-17.

- Checked: the figure 0.86 is on the page; its label is our wording.
- Checked: the passage quoted above is copied word for word from the page, near the name of xAID.
- Checked: each number in our summary is printed on the page.
- Checked: xAID uses Nebius AI Cloud. Confirmed line. Latest check across sources: 2026-10-17.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/xaid-nebius · How we check: https://www.usedby.ai/methodology