Then I guess all that it changes is that my proposed setup gets even better?

Huh? This is a new checkpoint. It has identical architecture, only different weights, and most likely just more post-training.

Much like Qwen 3.8 Next; which is qwen4-exp in a lot of the code/patches, there's usually a tick-tock cycle with LLMs. That said, it's hard to know for closed frontier models.

It's not identical, it has vision built in and asymmetric active from encode to decode.

DeepSeek delivery deliberately uses confusing version numbers.

4.1 flash was already multimodal. What do you mean by "It's not identical, it has vision built in..."

Sorry I forgot that already happened with the release last month and thought it was new in this one.