I mean, yeah. The splats are not made to be balanced between each other. The themes that each splat is about are wildly different as well.

It’s neat the mechanics allow cross play between the games though. The world would strangely feel smaller if they normalized the power scale across every game line.

And call of duty takes 100 of those xD

You can offload them into ram. The response time gets way slower once this happens, but you can do it. I’ve run a 70b llama model on my 3060 12gb at 2 bit quantisation (I do have plenty of ram so no offloading from ram to disk at least lmao). It took like 6-7 minutes to generate replies but it did work.