[sim04ful]

"We're also launching GPT‑5.6 Sol on Cerebras at up to 750 tokens per second in July, bringing frontier intelligence to customers at unprecedented speed. Access will initially be limited to select customers as we expand capacity."

This seems like it would be the largest and first closed-source model Cerebras has offered till date

[ComputerGuru]

Codex Spark models already run on Cerebras

[mekpro]

codex spark is not large model though, much weaker than standard model.