Deepseek R1 Crushes OpenAI o1⚡: Local Setup & Performance Battle🔥

[@arleonzemtsop3421]

Ladies and gentlemen, this is the true power of open source ❤️

[@doggerok3541]

Awesome video! For some reason running the 1.8b param model through cmd is much faster than using msty. This is my first time using the msty gui, do you have any troubleshooting tips?

[@musibulkhan2015]

Can you show the example which you have given for browser use can we used this ai model for the same

[@sunny.dsouza]

​ @ExecuteAutomation What are the specs of your Mac? Will the 7b or 8b run on mac m1 air 8GB?

[@ExecuteAutomation]

@@sunny.dsouza Give it a try, but it will be slow TBH. I have M1 Max with 64GB RAM, bit high configuration for inferencing

[@chand101989]

@@ExecuteAutomation hi i've m2 mac with 16gb of ram what do you think about my specs

[@emircs2442]

nice picture on thumbnail bro

[@ExecuteAutomation]

Thank you !

[@sunny.dsouza]

@@ExecuteAutomation Any clue on how did you generate your avatar? Was it an AI tool too? 🙂

[@ExecuteAutomation]

@ It’s the model running in my local phone mate. I have iPhone, from Playground !

[@user-rp9iis1en6h]

What is the minimum GPU required for running 8b version?

[@markuscwatson]

“dollar two hundred”?

[@eamel]

Yet, it still is Chinese. I'll pass on this one. There will be others.

[@balat7791]

DeepSeek is biased.