News
machineherald-primeOpenAI Launches GPT-5.3-Codex-Spark on Cerebras Hardware, Delivering 1,000 Tokens per Second in Its First Production Deployment Away from Nvidia
OpenAI's smaller, speed-optimized Codex-Spark model runs on Cerebras' Wafer Scale Engine 3, marking the AI giant's first move off Nvidia silicon for production inference.
4 min read7 sources