Cerebras

Cerebras brand colours

Extracted from the artwork and ranked by how much of the mark each covers, not from a brand book, so treat them as observed rather than official.

Cerebras serves open-weight models from wafer-scale engines and consistently posts the highest single-stream throughput measured in this category, often several thousand tokens per second on models where GPU hosts manage a few hundred. Like Groq it is a latency instrument rather than a general platform: a short model list, and an architecture decision you make deliberately.