Hugging Face Outage History
13 incidents recorded over the last 365 days, 13 of them resolved. Durations are measured from when PulsAPI first saw the problem to when it cleared, which is usually longer than the vendor's own figure.
Every Recorded Hugging Face Incident
| Date | Incident | Duration | Status |
|---|---|---|---|
| Oct 7, 2026 | Scheduled maintenance: Inference Endpoints (H200) | 4h 57m | Resolved |
| Sep 24, 2026 | Some GPU Jobs and Spaces failing to start | 391h 22m | Resolved |
| Sep 22, 2026 | Slower downloads in the Asia-Pacific region | 438h 34m | Resolved |
| Sep 16, 2026 | Scheduled maintenance: Hub | 2h 0m | Resolved |
| Sep 2, 2026 | Scheduled maintenance: Hub | 1h 0m | Resolved |
| Aug 17, 2026 | Scheduled maintenance: Spaces | 2h 0m | Resolved |
| Aug 7, 2026 | Elevated error rate - AWS CDN (Singapore) | 1546h 8m | Resolved |
| Jul 30, 2026 | Scheduled maintenance: Inference Endpoints | 28 min | Resolved |
| Jul 22, 2026 | Scheduled maintenance: Inference Endpoints | 1h 0m | Resolved |
| Jul 16, 2026 | Hub unavailable | 1839h 29m | Resolved |
| Jul 8, 2026 | Scheduled maintenance: Jobs | 1h 0m | Resolved |
| Jun 30, 2026 | Elevated error rate – AWS CDN (Singapore) | 1504h 1m | Resolved |
| Jun 10, 2026 | Data serving slowness in Asia region | 1984h 59m | Resolved |
Hear about the next one while it is open
Everything above is a record written after the fact. We can email you when the next Hugging Face incident opens instead, at the point where knowing still changes what you do.
Free, no password, no card. Unsubscribe in one click.
How to Read This Hugging Face Incident Log
Each row is an incident PulsAPI observed, not a summary written afterwards. The duration is wall-clock time between the first failing check and the first clean one, so it includes the window before Hugging Face acknowledged anything. Vendor post-mortems typically measure from acknowledgement, which is why their numbers are usually shorter.
Incidents still open have no duration yet and are listed as ongoing rather than being given a running total. The archive covers the last 365 days; anything older has aged out of the window rather than never having happened.
The longest single Hugging Face outage in this window ran 82d 16h, against a mean recovery of 24d 17h. If you depend on Hugging Face in a customer-facing path, the longest figure is the one to design around. The mean is what happens on a normal bad day; the maximum is what happens on the worst one.