With a gaming GPU you can run Qwen3.5-35B-A3B. I use 122B-A10B on my local rig (1x6000 Pro), and 397B-A17B on my 2x6000 Pro server (some spillover into CPU/RAM). It's pricey now but probably within a few years it'll become very affordable.
> Anthropic is already in a push to reduce costs and increase revenue
Yeah, it's totally a bad sign when a company tries to... reduce costs and increase revenue.
Usually in a land grab like this you spend, spend, spend.
Uber was still paying to subsidize customer's rides until fairly recently to kill off the competition.
When AI companies look to cut cost: a sign of bubble bursting.
When RAM price goes up: a sign of bubble bursting.
When RAM price goes down: a sign of bubble bursting.