Hi! I was wondering what is best LLM local model so far? Thanks in advance

Does anyone worked locally with this model? I would love to hear your opinions about it

Hi! I need help setting up Surya OCR. It works well—fast and accurate—but when it runs it uses 100% of the CPU, which prevents other processes from running smoothly. Could you share advice on how to configure it to reduce CPU usage or limit resource consumption? Thank you in advance!

I was wondering if anyone could tell me what they think the best OCR tools there are out there, with zero retention if possible. I played around with Mistral, PDF vector, Tesseract.... Was wondering if anyone has any better suggestions?

Hi guys! I have documentation full of scanned documents. What is the best way to parse them — should I use OCR or try to convert them into markdown? If OCR is the right approach, which OCR tool would you recommend? I need this in order to search thought data of this documents, these are invoices, contracts, etc. Thank you!