Partial Degradation of Qwen3 32B, Llama 3.1 8B, Llama 3.3 70B, and Qwen-3-235B-Instruct-2507
minor- Started
- Dec 12, 10:33 AM EST
- Resolved
- Dec 12, 1:04 PM EST
- Duration
- 2h 30m
Cerebras's updates (7)
- investigating · Dec 12, 10:33 AM EST
We are currently working to resume normal service performance. We will provide further updates as we make progress.
- investigating · Dec 12, 10:36 AM EST
We are continuing to investigate this issue.
- investigating · Dec 12, 10:37 AM EST
We are continuing to investigate this issue.
- monitoring · Dec 12, 10:58 AM EST
We've deployed the fix and affected service is now recovering. We are actively monitoring service performance.
- investigating · Dec 12, 12:47 PM EST
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, 12:48 PM EST
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, 1:04 PM EST
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.
Updates are Cerebras's own words from its status page (status: resolved); we never add an inferred cause. The vendor's incident page ↗