Live  /  Groq  /  Incident

Groq: meta-llama/llama-4-scout-17b-16e-instruct Degraded Performance

Groq · groq.comMinor incidentResolved2025-12-06 20:23 UTC
Public — what happened

Summary

Groq said that starting at 18:58 UTC on December 6, 2025, users of its meta-llama/llama-4-scout-17b-16e-instruct and groq/compound models could see more errors and slower responses, while its other models kept working. At 19:32 UTC the company reported the same kind of trouble on meta-llama/llama-4-maverick-17b-128e-instruct, which it said had cleared up by 19:59 UTC. Groq did not name a cause, but said it applied a fix for the Scout model and saw improvement, then declared all three models back to normal at 20:23 UTC.

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 Groq 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 Groq: its full incident track record, what tends to break, and recent public reports of problems.

Included with any paid plan.

Open the Groq report →

More from Groq

The full archive is on the Groq status & history page.

Related: Groq status & history. SquidGrid is not affiliated with Groq.