Qwen 3.8 27B available on Cerebras at 1500 tok/SEC
Summary
The Cerebras documentation highlights that Qwen 3.8 27B is available on Cerebras public endpoints with a throughput of about 1500 tokens per second, and provides context on model catalog, compression, and usage guidelines. It emphasizes that public models are unpruned and explains quantization/pruning concepts, with links to rate limits, pricing, and dedicated endpoints.