Qwen 3.8 27B available on Cerebras at 1500 tokens/s
Cerebras Inference has added the Qwen 3.8 27B model to its model catalog, as shown on the company's model overview page. The listing indicates that the model is available at a speed of 1500 tokens per second. This makes the Qwen 3.8 27B model accessible through Cerebras' inference service, which is designed for high-performance AI workloads. The exact model name, Qwen 3.8 27B, and the speed figure of 1500 tokens per second are directly stated in the source. The availability of this model on Cerebras' platform suggests that developers can now leverage this specific model for their inference needs, potentially benefiting from the high throughput offered by Cerebras hardware.
Developers can now run Qwen 3.8 27B at 1500 tokens per second on Cerebras.