> Inference really doesn't need that much power. I live on solar and run
> decently large models on my own equipment.
i think they meant LLM model training which uses way more power than
inference. and most people just use pre-trained stuff like
chatgpt/etc which are huge models so i bet their training power cost
is very high compared to a small (trained with non-enterprise
hardware) locally trained model
No comments:
Post a Comment