> CS-4 delivers more than 1,000 tokens per second on models exceeding 10 trillion parameters
Oops did they just out GPT-5.6 sol’s parameter count?
cerebras model are different size then the original models
I mean we kinda know the frontier models are multi trillion parameter models. The only open weights that are close to the frontier are that size too
Sol is supposed to be 5T according to rumour. The imminent Astra is allegedly 10