Hugging Face Outage History
Hugging Face is up right nowPingoru has recorded 31 incidents for Hugging Face: 31 in the last 12 months and 5 in the last 90 days.
Show as a table
| Month | Incidents | Hours with an open incident |
|---|---|---|
| April 2026 | 6 | 0 of 720 (0%) |
| May 2026 | 1 | 0 of 744 (0%) |
| June 2026 | 3 | 4 of 720 (1%) |
| July 2026 | 7 | 2 of 744 (0%) |
| August 2026 | 3 | 8 of 744 (1%) |
| September 2026 | 2 | 72 of 720 (10%) |
| October 2026 | 0 | 0 of 553 (0%) |
Incidents, newest first
Minor September 24, 2026 Some GPU Jobs and Spaces failing to start 15h 57m section-203447 (Spaces Proxy), section-337505 (Jobs), section-203447 (Spaces Proxy), section-337505 (Jobs)
Started Sep 24, 2026, 06:00 PM UTC· resolved Sep 25, 2026, 09:57 AM UTC
- investigating Sep 24, 2026, 06:00 PM UTC
Between 18:00 UTC on September 24 and 09:10 UTC on September 25, some GPU Jobs and GPU Spaces failed to start. Affected jobs ended with an ERROR status before the container started.
- resolved Sep 25, 2026, 09:57 AM UTC
The issue is resolved. If your job failed between 18:00 UTC on September 24 and 09:10 UTC on September 25, please resubmit it. If your Space is still showing a Runtime error, restart it from the Space settings.
Minor September 22, 2026 Slower downloads in the Asia-Pacific region 2d 23h section-317747 (AWS CDN), section-317747 (AWS CDN)
Started Sep 22, 2026, 06:48 PM UTC· resolved Sep 25, 2026, 06:42 PM UTC
- investigating Sep 22, 2026, 06:48 PM UTC
We're seeing slower download speeds for some users in the Asia-Pacific region who are served by our Singapore CDN location. Reduced network capacity between cloud regions is impacting our ability to download files that aren't already cached in the region. We are not seeing an increased error rate, so downloads should complete successfully. To reduce the impact, we're sending some Asia-Pacific traffic to our other CDN locations. Some users may see higher latency while this is in place. We're monitoring this closely and will post updates as things change.
- resolved Sep 25, 2026, 06:42 PM UTC
The upstream network capacity issue affecting our Singapore CDN location has been resolved, and download performance for Asia-Pacific users is back to normal. We've returned traffic routing to its usual configuration. Thank you for your patience.
Minor August 7, 2026 Elevated error rate - AWS CDN (Singapore) 8h section-317747 (AWS CDN), section-317747 (AWS CDN)
Started Aug 07, 2026, 03:14 PM UTC· resolved Aug 07, 2026, 11:14 PM UTC
- investigating Aug 07, 2026, 03:14 PM UTC
Some file downloads from our Singapore region (ap-southeast-1) failed with 500 errors during two short periods, starting at 15:14 UTC. Downloads are normal again now. The cause is not fully resolved, so short bursts of errors can return until our fix is in place. Other CDN regions are not affected. We are sorry for the disruption.
- resolved Aug 07, 2026, 11:14 PM UTC
Our fix is now in place and this incident is resolved. Applying it caused one final short period of failed downloads between 23:00 and 23:14 UTC, as we noted could happen. Downloads from the Singapore region have been stable since, and we have added capacity to prevent this from recurring. We are sorry for the disruption.
Minor August 6, 2026 Git Hosting and Serving recovered –
Started Aug 06, 2026, 06:48 PM UTC· resolved Aug 06, 2026, 06:48 PM UTC
No vendor updates were posted for this incident.
Minor August 6, 2026 Huggingface Hub recovered –
Started Aug 06, 2026, 06:46 PM UTC· resolved Aug 06, 2026, 06:46 PM UTC
No vendor updates were posted for this incident.
Minor July 25, 2026 Spaces Proxy recovered –
Started Jul 25, 2026, 01:36 AM UTC· resolved Jul 25, 2026, 01:36 AM UTC
No vendor updates were posted for this incident.
Minor July 16, 2026 Jobs recovered –
Started Jul 16, 2026, 08:45 AM UTC· resolved Jul 16, 2026, 08:45 AM UTC
No vendor updates were posted for this incident.
Major July 16, 2026 Hub unavailable 1h 37m section-3589 (Huggingface Hub), section-3589 (Git Hosting and Serving), section-203446 (Inference Endpoints UI), section-3589 (Huggingface Hub) and 1 more
Started Jul 16, 2026, 08:30 AM UTC· resolved Jul 16, 2026, 10:07 AM UTC
- investigating Jul 16, 2026, 08:30 AM UTC
Hugging Face platform is unavailable from most regions in the world due following a global outage from Amazon Web Services. We are working on a mitigation.
- resolved Jul 16, 2026, 10:07 AM UTC
Services are back to nominal operations. Root cause confirmed to global Amazon Web Services outage.
Minor June 30, 2026 Elevated error rate – AWS CDN (Singapore) 7m section-317747 (AWS CDN), section-317747 (AWS CDN)
Started Jun 30, 2026, 07:58 AM UTC· resolved Jun 30, 2026, 08:05 AM UTC
- investigating Jun 30, 2026, 07:58 AM UTC
Between 07:58 and 08:05 UTC, the AWS CDN returned an elevated rate of HTTP 500 errors for a portion of requests in the Asia-Pacific (Singapore / ap-southeast-1) region. The cause was a transient internal service disruption, which has been mitigated.
- resolved Jun 30, 2026, 08:05 AM UTC
Resolved. Error rates returned to normal at 08:05 UTC and the CDN is operating normally. The disruption lasted approximately 7 minutes. We apologize for any inconvenience.
Minor June 23, 2026 Inference Endpoints UI recovered –
Started Jun 23, 2026, 08:06 AM UTC· resolved Jun 23, 2026, 08:06 AM UTC
No vendor updates were posted for this incident.
Minor June 10, 2026 Data serving slowness in Asia region 3h 50m section-317747 (AWS CDN), section-317747 (AWS CDN)
Started Jun 10, 2026, 07:00 AM UTC· resolved Jun 10, 2026, 10:50 AM UTC
- investigating Jun 10, 2026, 07:00 AM UTC
We are experiencing slowness on large file downloads in Asia region since 7AM UTC. This only affects downloads via the huggingface CLI. Root cause identified and mitigation in progress.
- resolved Jun 10, 2026, 10:50 AM UTC
Issue is solved, Asia traffic back to nominal bandwidth performances.
Minor March 10, 2026 Google cloud CDN recovered –
Started Mar 10, 2026, 02:45 PM UTC· resolved Mar 10, 2026, 02:45 PM UTC
No vendor updates were posted for this incident.