Cerebras incident
Partial Degradation of Qwen3 32B, Llama 3.1 8B, Llama 3.3 70B, and Qwen-3-235B-Instruct-2507
Cerebras experienced a minor incident on December 12, 2025 affecting Llama3.1-8B and Qwen-3-235B-Instruct-2507, lasting 2h 30m. The incident has been resolved; the full update timeline is below.
Affected components
Update timeline
- investigating Dec 12, 2025, 03:33 PM UTC
We are currently working to resume normal service performance. We will provide further updates as we make progress.
- investigating Dec 12, 2025, 03:36 PM UTC
We are continuing to investigate this issue.
- investigating Dec 12, 2025, 03:37 PM UTC
We are continuing to investigate this issue.
- monitoring Dec 12, 2025, 03:58 PM UTC
We've deployed the fix and affected service is now recovering. We are actively monitoring service performance.
- investigating Dec 12, 2025, 05:47 PM UTC
Between 06:50 AM PST and 07:45 AM PST users experienced partial degradation with llama3.1-8b, llama-3.3-70b, qwen-3-32b, qwen-3-235b-instruct-2507 models. We have deployed a fix and the issue is now resolved.
- investigating Dec 12, 2025, 05:48 PM UTC
Between 06:50 AM PST and 07:45 AM PST users experienced partial degradation with llama3.1-8b, llama-3.3-70b, qwen-3-32b, qwen-3-235b-instruct-2507 models. We have deployed a fix and the issue is now resolved.
- resolved Dec 12, 2025, 06:04 PM UTC
Between 06:50 AM PST and 07:45 AM PST users experienced partial degradation with llama3.1-8b, llama-3.3-70b, qwen-3-32b, qwen-3-235b-instruct-2507 models. We have deployed a fix and the issue is now resolved.