Log inSign up
Alex Ziskind
13.7K posts
user avatar
Alex Ziskind
@digitalix
Software engineer making videos about dev gear, local AI, and weird tech experiments
Washington DC, USA
youtube.com/@azisk
Joined March 2009
1,483
Following
22.6K
Followers

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
  • user avatar
    Alex Ziskind
    @digitalix
    Sep 20, 2025
    This is how apple has that high adoption
    1.3M
  • user avatar
    Alex Ziskind
    @digitalix
    Oct 15, 2025
    every day now
    636K
  • user avatar
    Alex Ziskind
    @digitalix
    Mar 15, 2025
    power consumption at idle with Mac Studio cluster
    00:00
    623K
  • user avatar
    Alex Ziskind
    @digitalix
    Sep 24, 2025
    really not happy with ios 26. I’m at 4% and it’s only 6:30pm. Apple made my iphone 16pro a half-day phone and i’ve had it for less than a year.
    458K
  • user avatar
    Alex Ziskind
    @digitalix
    Nov 19, 2024
    m4 mac mini cluster with 5 nodes running exo
    00:00
    363K
  • user avatar
    Alex Ziskind
    @digitalix
    Feb 8, 2025
    my first NVIDIA RTX 5080 test with ollama
    00:00
    287K
  • user avatar
    Alex Ziskind
    @digitalix
    Nov 19, 2024
    all 5 to the max. pretty quiet in here
    00:00
    137K
  • user avatar
    Alex Ziskind
    @digitalix
    Sep 16, 2023
    why does this keep happening? does every language need its own IDE or is it just easier to market these dedicated tools?
    358K
  • user avatar
    Alex Ziskind
    @digitalix
    Jun 11, 2025
    what have they done
    00:00
    235K
  • user avatar
    Alex Ziskind
    @digitalix
    Jul 20, 2025
    Sorry, but I’m still on “how’d they get a Gigabyte in that tiny card?”
    314K
  • user avatar
    Alex Ziskind
    @digitalix
    Apr 8, 2025
    mlx distributed uses mpi for machine to machine communication, and this is how you can handle uneven distribution of model layers. Thanks @awnihannun for the help
    00:00
    32K
  • user avatar
    Alex Ziskind
    @digitalix
    Mar 5, 2025
    hoping for M4 Ultra with 256GB memory. Got M3 Ultra with 512GB.
    41K
  • user avatar
    Alex Ziskind
    @digitalix
    Jul 31, 2025
    Qwen3 Coder FLIES on the M4 Max vs RTX 5090
    00:00
    50K
  • user avatar
    Alex Ziskind
    @digitalix
    Oct 14, 2025
    so… how about M5 Pro with 128GB RAM?! anyone think it’s happening?
    31K