Difference between A100 vs RTX 4090 in training deep learning models

[jack_calla]

What are the differences between A100 and RTX 4090 for training deep learning models? Does using A100 make the model more accurate, I mean using A100 the model output is more reliable than 4090 and the model is trained better?

[AakankshaS]

Hi @jack_calla ,
I might not be his forum talks about issues related to Tensorrt,
However maybe this thread can help

Which one is more suitable for my needs? A100 or 4090?

Hi there, I want to process 10 billion data for filtering, sorting, and aggregation, and query some specific data within seconds. Right now I have several choices, e.g. A40, A100, or 4090. I want to know which one is better for me. Indeed, I don’t need the 3-party tensor support by A100, if I only consider CUDA cores and bandwidth, it seems 4090 is a better choice. Could you offer me some advice? Thx

[jack_calla]

Thank you for your guidance.
But I am looking for the answer to this question: does using A100 have a significant impact on the accuracy and performance of the model?