Fresh install of start9.
Models are installing fine, no errors in the start9 logs, plenty of CPU/memory available…
This is what it’ll look like, regardless of the prompt or model I choose:
Any ideas?
Fresh install of start9.
Models are installing fine, no errors in the start9 logs, plenty of CPU/memory available…
This is what it’ll look like, regardless of the prompt or model I choose:
Any ideas?
How long is it staying in this state? Sometimes, depending on the specific model you choose and the RAM you have available, response time can be slow.
Please provide extra details on the hardware you are using to see if there are any issues there.
This is it, this is the only state that is output after I enter my prompt. You could almost say it freezes there.
Are your heath checks for FreeGPT green?
Take a look at the logs of Free GPT and see what’s going on. Look for error messages
Check system → monitor to see how heavy a load is being put on your system.
Try a smaller model if you think you might be lacking resources. I like smollm2:latest for example.
I assume you tried stopping and restarting the service and/or the server itself. That never hurts
Thank you!
I checked system resources, and sure enough, even using a smaller model, CPU would spike to 100% after prompting.
Looks like it’s time to use a more powerful machine!
This topic was automatically closed 2 days after the last reply. New replies are no longer allowed.