Live  /  Hugging Face  /  Incident

Hugging Face: Elevated error rate - AWS CDN (Singapore)

Hugging Face · huggingface.coMinor incidentResolved2026-08-07 23:14 UTC
Public — what happened

Summary

Hugging Face reported a minor incident involving a higher-than-normal rate of errors on its AWS content delivery network in the Singapore region, beginning at 15:14 UTC on August 7, 2026. The company said that putting its fix into place led to one last brief stretch of failed downloads from 23:00 to 23:14 UTC, which it had warned might happen. Hugging Face marked the issue resolved at 23:14 UTC, saying Singapore downloads have been steady since then and that it has added capacity to keep the problem from happening again.

Timeline

Source of record: provider status page. Summary written by SquidGrid from the provider’s published updates; times in UTC.

Independent path health

The status page is the symptom. SquidGrid measures the paths that reach Hugging Face against their own baselines — whether the routes carrying your traffic degraded, at which handoff, and who owns that stretch.

🔒 Sign in to see
Customers get the live Provider Assessment Report for Hugging Face: its full incident track record, what tends to break, and recent public reports of problems.

Included with any paid plan.

Open the Hugging Face report →

More from Hugging Face

The full archive is on the Hugging Face status & history page.

Related: Hugging Face status & history. SquidGrid is not affiliated with Hugging Face.