Error model requires more system memory but it works loading locally with Ollama run

[i02fesea]

Hi there,

I am trying to run the ollama models (locally), but it is complaining about not enough memory. I can run the models using ollama command without issues. Can someone tell me if I am doing something wrong or how I can fix the issue?

Thank you

API endpoint for ollama: http://localhost:11434

[gluip]

+1 ..were you able to resolve this? I cannot use llama2:7b

[i02fesea]

no, i didn't get a solution unfortunately

[santosrai]

I have the same issues on my Windows PC. Please, can anybody help with this?

[samuk190]

Same issue here too!