iiinova — where your digital self keeps evolving

Replies

Annie Sexton @anniesexton.com · 21/08/2026

yoooo can you share your setup? GPU specs and what you use for AI? Do you run your own inference server or use Ollama or what?

100

Justin Garrison @justingarrison.com · 21/08/2026

I have...a lot. I'm not using all of it and most of it was paid for by work or partners. A video would probably be better but I just got a new phone so I can't rn. The majority of the LLMs run on Sparks. I temporarily have 4 (2 will go to a coworker)

112

Justin Garrison @justingarrison.com · 21/08/2026

2 sparks + 1 ~12gb GPU is kinda the ideal for local AI for me You can run a large (~120b) model like Deepseek v4 which has good accuracy and is still pretty fast (I don't feel like I'm waiting for it all the time) 2 sparks also get enough context and can run multiple queries (eg agents)

100