Hi,
would the mac be a good machine for having lots of smal models in memory - ready for action - like whisper, an llm, tts, llava and use em sequentially or maybe max two in paralell?
(in respect to the 400gbit bandwidth limitation)
i d like to make a powerful agent, like a brain with many brainparts responsible for specific stuff
cute ☺️ no reason to start cutting the wifi cables