Qwen 3.8 27B available on Cerebras at 1500 tokens/s

Altertable's announcement that Qwen 3.8 27B runs at 1,500 tokens per second on Cerebras hardware earned 540 points and 172 comments, positioning this as the go-to option for developers prioritizing inference speed over model size.

View Source

Comments on "Qwen 3.8 27B available on Cerebras at 1500 tokens/s"

Have a take on this ranking?

Comments are how the argument actually happens here. Posting one needs a free account — it takes about a minute.

Create a free account Already have one? Sign in

No comments yet.

The first comment sets the terms of the argument.

Photos (1)

Comments on "Qwen 3.8 27B available on Cerebras at 1500 tokens/s"