When I use the gemini2.5pro chat model on a self-hosted system, the processing is too heavy and it won’t run

Questions
1

When I use the gemini2.5pro chat model on a self-hosted system, the processing is too heavy and it won’t run.
When using the gemini2.5pro chat model on a self-hosted system, how much memory and CPU does the self-hosted system require?

2

i think it is a bug with all ai agent cpu is spiking

3

Would this happen if I have too little memory? What is the minimum memory required?

4

I tried with 16 cpu, its the same goes 100% for no reason.

5

Hi, could you share your workflow and what version you are using? I have been using the ai agent with gemini models with no issues.

2 Likes
6

This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.