Are we getting Qwen 3.8 35-A3B?

So far, it seems like Qwen 3.8 might drop today as a 27B dense model. If that’s the case, no MoE offloading this time , I used to run Qwen 3.6 35B-A3B at around 70 tok/s on an RTX 3060, but offloading a dense model is a completely different story it can be 100× slower or Even slower submitted by

中文全文翻译正在补齐，可先查看下方英文原文。

So far, it seems like Qwen 3.8 might drop today as a 27B dense model. If that’s the case, no MoE offloading this time , I used to run Qwen 3.6 35B-A3B at around 70 tok/s on an RTX 3060, but offloading a dense model is a completely different story it can be 100× slower or Even slower submitted by