Do you have evidence to prove that "And for a 14,000 token context window, M2 Ultra may take as long as 20 or more *minutes* to start responding. " 70b model int4 quantization?
Sorry I open two threads at same time ，and I put the wrong one.
However，Oryon is the spiritual successor to Firestorm, extensively reusing Firestorm's design.
A user named qzyqzy achieved a score of 4009 on the M4. He might have used a secret method to ensure every device received an exceptionally high score. For reference, the A17 Pro scored 3044, and the M3 Max scored 3267.
https://browser.geekbench.com/user/qzyqzy
here is the spec2017 int test by JHT5132 in baidu tieba with additional cooling (icebag)
整机 means total power
减空载 means total power minus idle power. By the way, my test score of M3 pro is lower than 10
Here is the link https://browser.geekbench.com/v6/cpu/6089998
It was a contest on China social media, one guy put his ipad in frozen freezer to get 3934, Geekerwan decided to go with liquid nitrogen for better results
Maybe it is the first time to use Liquid nitrogen cooling ARM chip? The M4 is so difficult to gain 4.42Ghz in room temperature . The guys in Geekerwan use Liquid nitrogen to get the best performance of geekbench. M4 get 3977 for Geekbench 6 and 2754 for Geekbench 5.
This site uses cookies to help personalise content, tailor your experience and to keep you logged in if you register.
By continuing to use this site, you are consenting to our use of cookies.