Well if you're spending thousands on API tokens already, you could just drop the same amount on a 128GB MacBook Pro and that's a one time cost.
If you're dropping thousands on API tokens, you're going to be slowed down at least 10x trying to do everything on a single MBP.
But you could grab a 5090, and paired with some DRAM for MoE offloading of bigger models, and be a happy camper with 1.8TB/s of memory bandwidth.
Or just use Luna honestly. Worth considering if you’re ok with hosted APIs.
Don't forget about energy usage, you'll probably never break even vs same model on openrouter.
If you can’t do it cheaper on your own hardware it does make you wonder how much of the cost of inference those large LLM providers are eating? Datacenter hardware isn’t magic.
loading story #49243249
loading story #49242901
loading story #49243685
The models people are spending thousands on require more on the range of 600-800gb memory.
128gb hardly runs deepseek v4 flash which is almost free via api pricing.