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
- Started — 2025-11-04 02:11 UTC
- Identified — 2025-11-04 02:11 UTC
- Monitoring — 2025-11-04 02:33 UTC
- Resolved — 2025-11-04 02:47 UTC · 37 min after it started
With SquidGrid — where it starts on the route
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 seeCustomers 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