No it definitely doesn't make economic sense right now. My Hermes runs Qwen 3.6 on an old gaming computer that cost me about $300, but its far slower and dumber than deepseek v4 flash.
Ok
Thanks
Makes sense
So I won't have fun and joy of running a model on my own hardware
Too expensive
Maybe in the future if models get even more efficient
Because hardware isn't going to get cheaper, at least not in dollar terms
Thanks
Makes sense
So I won't have fun and joy of running a model on my own hardware
Too expensive
Maybe in the future if models get even more efficient
Because hardware isn't going to get cheaper, at least not in dollar terms