Live  /  Groq  /  Incident

Groq: Model Performance Issue: llama-3.1-8b-instant

Groq · groq.comMinor incidentResolved2025-11-04 02:47 UTC
Public — what happened

Summary

Groq reported a minor problem with its llama-3.1-8b-instant model on November 4, 2025, beginning at 02:11 UTC, saying users could see slower responses while a fix was underway. By 02:33 UTC the company said a fix had been applied, performance was getting better, and it was watching the model for stability. Groq declared the incident resolved at 02:47 UTC and said the cause was two recent code changes linked to increased latency, which it rolled back.

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.