@digitalix

Software engineer making videos about dev gear, local AI, and weird tech experiments

 Washington DC, USA
youtube.com/@azisk
Joined March 2009
  • Tweets14.3K
  • Following1.5K
  • Followers28.9K
2.4KMedia
B&H has their shit together. You want to try something, everything is hooked up and just works
1
34
2,277
I had a bunch of these and none of mine were as pleasurable.
BijanBowen
@bijanbowenOct 21
Why are some DGX Sparks ribbed for pleasure underneath while others aren't????
9
1
80
7,062
Had dinner last night with 7 people, 5 had foldables, 2 had iphones. Things are about to change. Here come the duos. I gotta wait for mine another month and a half
7
1
27
2,975
Tonight in NYC I'm on stage at ASUS Creator Connect, part of NAB Show New York. I'll show you AI that can actually watch your footage, running locally on two ASUS machines. Pier59 Studios, 6 to 10pm 👇
Alex Ziskind
@digitalixOct 19
I’m racing the the GX10 DGX Spark vs ExpertCenter Pro ET900N G3 (DGX Station). Is the extra $$$ worth the speed?
1
1
52
2,698
info here: asus.com/microsite/agent-com…

ASUS Powering Every AI Choice | The Right Agent Computer for Cloud, Local, or Hybrid AI.

Find the ASUS agent computer that fits your workflow—compare CPU, GPU & memory specs for AI computing across laptops, mini PCs & NUCs, custom PC Build, desktops, and workstations.

asus.com
3
584
im pretty impressed with the new ASUS p16 RTX Spark laptop. I might try daily driving it for a bit. MacBook has a slightly taller screen, but it’s the menu bar
37
17
1
564
57,242
im going to bet that opus 5.5 will not do this. but 4.8 might
@levelsio
@levelsioOct 20
OK why not
21
1
1
140
8,430
🤔
@levelsio
@levelsioOct 20
OK why not
2
42
3,278
I’m racing the the GX10 DGX Spark vs ExpertCenter Pro ET900N G3 (DGX Station). Is the extra $$$ worth the speed?
28
5
4
244
17,362
gb300 in desktop is one incredible machine.
Harrison Kinsley
@SentdexOct 17
dario begged me in dms to not do agent swarms at home but whatever, this is nemotron 120B A12B running 64 concurrents at a bit over 100 tok/sec each for an aggregate of almost 7K tok/sec on a single GB300 (Asus DGX Station) believe it or not, the agents did NOT magically just start hacking the planet tho. weird.
10
3
2
190
22,169
Alex Ziskind retweeted
sparkarena
@spark_arenaOct 17
🟢 Spark Arena is going all green! Eugene (@eugr) joined NVIDIA back in May, and now Raphael (@raphafacts) and Drew (@DrewBotwinick) are joining too! All three of us will be working on local AI engineering team at NVIDIA, but Spark Arena isn't going anywhere. We're excited to keep building, benchmarking, and growing this community together! 🚀 @NVIDIAAI @NVIDIARTXSpark @nvidia
29
7
104
7,490
fast prompt processing, but low memory bandwidth
Alex Ziskind
@digitalixOct 17
let’s go
4
1
73
3,939
let’s go
20
1
1
275
9,008
my first RTX Spark tests for devs and AI (new video)
23
9
3
188
11,287
video here: youtu.be/iZ88PPiAsl8

NVIDIA Put a DGX Spark in a Laptop… Almost

I put the MSI's RTX Spark, up against my DGX Spark, then pulled the...

youtube.com
2
3
15
1,725
wow. december
40
6
1
184
8,699
two versions, including nvfp4 out the gate, but with seemingly less params.
Alex Ziskind
@digitalixOct 15
What's this? New model gonna need these bad boys. Meta's 816B param Muse Spark is open wieghts 🤯 1M-token context window. And MoE, so likely relatively fast. Now I'm really curious what my cluster can do!
7
1
1
48
6,636
What's this? New model gonna need these bad boys. Meta's 816B param Muse Spark is open wieghts 🤯 1M-token context window. And MoE, so likely relatively fast. Now I'm really curious what my cluster can do!
28
16
3
511
21,510
guess who (or what): "You’re right, and that’s on me."
15
39
5,347
Dedicated GPU memory, IN WINDOWS!
Alex Ziskind
@digitalixOct 14
192GB RAM in a box. Ryzen AI Max+ Pro 495. This one by GMKtec. let’s plug it in
28
9
2
424
25,167
Load more