Replying to Avatar U-P-G-R-A-Y-E-D-D

Running a local model is the most private. It's pretty easy to fo with Ollama and OpenWebUI

If you don't want to spend $500 on a GPU, then Venice (supported by Erik Voorhees) looks like a pretty good option :

https://venice.ai/?r=0

Avatar
Diyana 10mo ago

I'd really love to be able to soon upgrade my machine and run local for sure. It's my dream. :)

Reply to this note

Please Login to reply.

Discussion

Avatar
⚡ Dee Kay ⚡🇸🇪🇬🇧🇨🇿🇧🇷🇦🇹 10mo ago

You can even run on phone now 😂

Oterwise https://venice.ai/ is a good option as mentioned.