If LLMs used very little RAM and processing power, was light weight even for Mythos or Sol, would people be as opposed? Like no data centers, no memory shortages, like it was able to run on a calculator with the same performance.
If LLMs used very little RAM and processing power, was light weight even for Mythos or Sol, would people be as opposed? Like no data centers, no memory shortages, like it was able to run on a calculator with the same performance.
It’s designed to be scalable. You can already run basic models on home hardware, but available resources determine speed and power.
If you could get today’s results on 1/10 the RAM/electricity, that would be good, but the big companies would just scale up to use the same resources anyway.