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

Washington DC, USA
Joined March 2009
but after all that, ended up running the dgx station off a 120V 20a outlet and it was perfectly fine
some might say it’s overkill to pack 240V extensions and adapters. but the venue where I demos the dgx station last night didn’t have a 240V extension so glad I brought it.
4
1
15
1,508
some might say it’s overkill to pack 240V extensions and adapters. but the venue where I demos the dgx station last night didn’t have a 240V extension so glad I brought it.
2
2
20
2,364
Matching switch!
Found my kind of place at @NVIDIAAI GTC Berlin. Including the (for now) proof-of-concept switch. I counted 2 pairs of 5 ports - so you’d be able to pair up to 10 DGX Spark systems with breakout cables.
4
32
2,187
B&H has their shit together. You want to try something, everything is hooked up and just works
1
37
2,550
I had a bunch of these and none of mine were as pleasurable.
Why are some DGX Sparks ribbed for pleasure underneath while others aren't????
9
2
87
8,131
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
33
3,408
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 👇
I’m racing the the GX10 DGX Spark vs ExpertCenter Pro ET900N G3 (DGX Station). Is the extra $$$ worth the speed?
1
1
52
2,830
im pretty impressed with the new ASUS p16 RTX Spark laptop. I might try daily driving it for a bit. MacBook has a slightly taller screen, but it’s the menu bar
37
17
1
565
57,492
im going to bet that opus 5.5 will not do this. but 4.8 might
21
1
1
141
8,499
I’m racing the the GX10 DGX Spark vs ExpertCenter Pro ET900N G3 (DGX Station). Is the extra $$$ worth the speed?
28
5
4
243
17,497
gb300 in desktop is one incredible machine.
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
22,192
Alex Ziskind retweeted
🟢 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
30
8
107
7,642
fast prompt processing, but low memory bandwidth
4
1
73
3,944
let’s go
20
1
1
275
9,017
wow. december
40
6
1
184
8,707
two versions, including nvfp4 out the gate, but with seemingly less params.
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
6,645