Alex Ziskind's banner

Alex Ziskind

@digitalix • 26,385 subscribers

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

Shorts

Each of these cards has a cool 144GB of HBM, and 4TB/s memory bandwidth. Yes please!

Each of these cards has a cool 144GB of HBM, and 4TB/s memory bandwidth. Yes please!

128,512 просмотров

32GB of VRAM for under $1000! The Intel Arc Pro B70 just landed.

32GB of VRAM for under $1000! The Intel Arc Pro B70 just landed.

1,121,305 просмотров

It's happening again. This time for real. Video coming shortly

It's happening again. This time for real. Video coming shortly

1,043,254 просмотров

DGX Spark GB10’s came in one memory config (128GB) and form factor (mini pc). RTX Sparks will have the full range: 16GB-128GB, and both laptops and desktops!

DGX Spark GB10’s came in one memory config (128GB) and form factor (mini pc). RTX Sparks will have the full range: 16GB-128GB, and both laptops and desktops!

208,680 просмотров

m4 mac mini cluster with 5 nodes running exo

m4 mac mini cluster with 5 nodes running exo

362,753 просмотров

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

trying to find the crease. It’s not easy. this is the first foldable that doesn’t immediately have an obvious crease. It’s there, but minimal.

trying to find the crease. It’s not easy. this is the first foldable that doesn’t immediately have an obvious crease. It’s there, but minimal.

404,707 просмотров • 17 часов назад

My first try with Omarchy Linux Linux and it's with non other than NetworkChuck

My first try with Omarchy Linux Linux and it's with non other than NetworkChuck

58,890 просмотров • 21 часов назад

power consumption at idle with Mac Studio cluster

power consumption at idle with Mac Studio cluster

623,323 просмотров • 1 год назад

Fast enough? GLM5.2 on the DGX Station via VSCode agent

Fast enough? GLM5.2 on the DGX Station via VSCode agent

50,668 просмотров • 1 месяц назад

what have they done

what have they done

235,312 просмотров • 1 год назад

my first NVIDIA RTX 5080 test with ollama

my first NVIDIA RTX 5080 test with ollama

287,087 просмотров • 1 год назад

8 sparks cluster running

8 sparks cluster running

111,427 просмотров • 6 месяцев назад

fastest way to move llms between machines for distributed inference

fastest way to move llms between machines for distributed inference

74,282 просмотров • 7 месяцев назад

that’s a lot of copper

that’s a lot of copper

22,360 просмотров • 1 месяц назад

all 5 to the max. pretty quiet in here

all 5 to the max. pretty quiet in here

136,971 просмотров • 1 год назад

ebay is going crazy

ebay is going crazy

31,885 просмотров • 4 месяцев назад

Qwen3.5 is huge! will it blend?

Qwen3.5 is huge! will it blend?

40,784 просмотров • 6 месяцев назад

Which DGX Spark is running Gemma 4?

Which DGX Spark is running Gemma 4?

25,291 просмотров • 4 месяцев назад

Dell DB300 coldpate is insane. Has to cover 3 areas and be completely flat and level, and have redundant pumps. Impressive design.

Dell DB300 coldpate is insane. Has to cover 3 areas and be completely flat and level, and have redundant pumps. Impressive design.

16,594 просмотров • 3 месяцев назад

most serviceable mini ive ever seen

most serviceable mini ive ever seen

18,065 просмотров • 4 месяцев назад

feel the struggle. building the smallest AI workstation.

feel the struggle. building the smallest AI workstation.

11,824 просмотров • 2 месяцев назад

found an amazing deal on the DGX Spark

found an amazing deal on the DGX Spark

23,408 просмотров • 6 месяцев назад

DGX Spark giveaway.

DGX Spark giveaway.

20,790 просмотров • 5 месяцев назад

GLM5 running on a cluster of 4 Mac Studios using tensor parallelism thanks to MLX distributed. Yes, those are the Alex drawers.

GLM5 running on a cluster of 4 Mac Studios using tensor parallelism thanks to MLX distributed. Yes, those are the Alex drawers.

20,594 просмотров • 6 месяцев назад