Model Performance or Availability Issue: llama-3.3-70b-versatile
Was Groq down? Groq reported “Model Performance or Availability Issue: llama-3.3-70b-versatile” on Dec 24, 2025, 11:01 PM UTC. Full timeline below. This incident affects Groq — see live Groq status. Source: official vendor status feed.
Timeline
Dec 25, 2025, 12:16 AM UTC
The issues affecting **llama-3.3-70b-versatile** have been **resolved**. The model is operating normally. We apologize for the disruption and thank you for your patience.
Dec 25, 2025, 12:04 AM UTC
We have **implemented a fix** for **llama-3.3-70b-versatile** and performance is improving. The team is continuing to work the issue and we hope to have it resolved shortly.
Dec 24, 2025, 11:01 PM UTC
We’ve identified an issue causing 503s for the `llama-3.3-70b-versatile` production model. We’ve started mitigation. Error rates are improving, but some requests may still fail while we continue tuning and monitoring.
More Groq outages
- Data Center Failure Impacting CapacityJul 1, 2026, 11:01 PM UTC · resolvedDegraded
- openai/gpt-oss-120b Performance IssueMar 19, 2026, 12:51 PM UTC · resolvedDegraded
- meta-llama/llama-4-scout-17b-16e-instruct Degraded PerformanceFeb 7, 2026, 10:02 AM UTC · resolvedDegraded
- meta-llama/llama-4-scout-17b-16e-instruct Degraded PerformanceFeb 5, 2026, 6:09 PM UTC · resolvedDegraded
- meta-llama/llama-4-scout-17b-16e-instruct Degraded PerformanceFeb 5, 2026, 1:23 PM UTC · resolvedDegraded
- meta-llama/llama-4-scout-17b-16e-instruct Degraded PerformanceJan 26, 2026, 11:17 PM UTC · resolvedDegraded