Skip to content
X · @teortaxesTex · X / Twitter

2.4T is a design Chinese hyperscalers like. Ernie 5 and ByteDance's experiments also used this number. Now Alibaba.

2.4T is a design Chinese hyperscalers like. Ernie 5 and ByteDance's experiments also used this number. Now Alibaba.AiBattle: The new Qwen 3.8-Max model has 2.4 trillion parameters and delivers significant improvements in coding and cowork compared to Qwen3.7-Max