Alex Ziskind

13.4K posts

Alex Ziskind

@digitalix

Developer and content creator, founder of @NativeScripting, ”the voice of NativeScript”, trainer, author, speaker, synth tweaker. https://t.co/ZjhwZDX24l

Washington DC, USA Katılım Mart 2009

1.5K Takip Edilen21.6K Takipçiler

Alex Ziskind retweetledi

Philippe Tremblay@ptremblay·14h

Early look at Etudera, my interactive music practice app. Built with GPT 5.5 in Codex. Synced notation + guitar tabs, playback, tempo control, looping, metronome, MusicXML import, and dark mode. Still early, but it’s starting to feel real. 🎸

English

2.1K

Alex Ziskind@digitalix·13h

@Everlier 🙃

QME

Everlier@Everlier·18h

@digitalix I am spearheading the development of a transformative containerized AI orchestration platform that empowers 10,000+ developers worldwide to deploy enterprise-grade local LLM infrastructure. yep

English

Alex Ziskind@digitalix·19h

yep

Louis-François Bouchard 🎥🤖@Whats_AI

AI engineers on LinkedIn vs what actually happened. Swipe and tell me if I'm wrong 😅

QST

3.6K

Alex Ziskind@digitalix·17h

@ivanfioravanti picking one or two is a hard problem. you’ll get 20 people with 20 different answers here

English

578

Ivan Fioravanti ᯅ@ivanfioravanti·17h

In a Local AI benchmark what should be the context length used as main reference for speed? We are all using very small context to showcase model speed in our hardware, but that's unrealistic.

English

6.6K

Alex Ziskind@digitalix·18h

@MarcW4OVT ah good deal!

English

Marc Bowen@MarcW4OVT·1d

Looks like you cruising the aisles at MC..."I'll take two of those...five of those...". Writing of, just got back from MC Charlotte with an Open-Box 16" MB Pro M5 Max w/64GB, max cores, 2GB SSD - $4.8K OTD...but what delivers tomorrow from B&H Photo is the big news = 2 x M3 Ultra "Big Boys!". HUZZA!!!

English

224

Alex Ziskind@digitalix·1d

Gemma is so much faster! wait, are the ghosts walking through walls? did they idspispopd?

tawer@tawer1O

Comparison of Gemma 4 and Qwen 3.6 in the same coding task Same hardware, same prompt, comparable model size > gemma 4 31b: 27 tok/s, 3m 51s, 6,209 tokens, stronger game logic > qwen 3.6 27b: 32 tok/s, 18m 04s, 33,946 tokens, better visuals Gemma 4 with lower tok/s finished 14 minutes faster because it used 5.5x fewer tokens to reach a complete answer

English

117

20.2K

Alex Ziskind@digitalix·1d

@ptremblay oooh. it can generate sheet music?

English

618

Philippe Tremblay@ptremblay·1d

Who said GPT 5.5 can't do front-end? It's coming along great, I think.

English

695

Alex Ziskind@digitalix·1d

@Ominousind ahead of its time

English

676

BijanBowen@Ominousind·1d

Interview I did for my GPT-3 social robot 3 years ago, I have never shared this on here

Matt Shearer@MattWBZ

Faces of the future. @Ominousind @wbznewsradio

English

5.4K

Alex Ziskind@digitalix·1d

@321baj well, i am on yt.

English

Basil Jackson@321baj·2d

@digitalix I used to really enjoy your videos... I think you have fallen to the YT fever, however.

English

Alex Ziskind@digitalix·2d

I split one LLM across a DGX Spark and a M3 Ultra Mac Studio to see if they would be faster together (new video)

English

268

22K

Alex Ziskind@digitalix·2d

@Authentic1ty @erictimmer asus has extra heat pipes if i remember correctly

English

Scott Jordan@Authentic1ty·2d

@digitalix @erictimmer ASUS also cools the best. The physical unit is larger and has better ventilation.

English

Alex Ziskind@digitalix·2d

@Kurcide @exolabs check out this cluster!

English

135

Marc Seal@Kurcide·2d

@digitalix Worth reaching out to them? Idk of another 16x spark cluster but would be happy to contribute to Exo and run tests on this

English

187

Alex Ziskind@digitalix·2d

@Kurcide pretty slick cluster you have there. i recommend waiting until the official support is out from exo, which should be pretty soon

English

698

Marc Seal@Kurcide·2d

@digitalix Just built a 16x DGX Spark cluster and want to test pairing with Mac studios for decode. Can we connect?

English

965

Alex Ziskind@digitalix·2d

@runsonai great work on the hybrid PR!

English

Thanh Pham@runsonai·2d

@digitalix Yep! Keep up the great content, watched a lot of your videos and ended up buying the machines so I could do local. Glad I could contribute back.

English

Thanh Pham@runsonai·2d

Watch @digitalix newest video to see how you can set this up too.

Thanh Pham@runsonai

4 hours of grinding. Running on untested branches to make nvidiva gb10 chip work with mac studio on the same cluster. But I got it working now @exolabs! Running Qwen 3.5 27b, 2100+ t/s prefill speed on my gx10, 19 t/s on studio, 4200ms ttft. Not bad before optimization.

English

1.3K

Alex Ziskind retweetledi

Thanh Pham@runsonai·2d

@digitalix Thanks for showing my PR at 2:06 that made this work. Spent countless hours figuring out how to connect my GX10 and Studio, and glad you used it to show everyone what's possible. It's been fun tinkering with local models this way.

English

Alex Ziskind retweetledi

David Hendrickson@TeksEdge·2d

You really have to check out @digitalix's latest video on disaggregation. He really doesn't spare any detail. It's painful work, but he gets things running and explains results. IMHO, local inferencers are being ignored by BigTech and BigAI, but Alex is looking out for us. 🙂