Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

.Ahmad stopped by MTS with a NVIDIA DGX Station (Dell Technologies Pro Max with GB300). 🔥 Thousands of tokens per second all running locally.

NVIDIARTXSpark's profile picture

NVIDIA RTX Spark

55,762 subscribers

12,130 Aufrufe • vor 10 Tagen •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

11 Kommentare

Profilbild von Ahmad
Ahmadvor 10 Tagen

@MTSlive @Dell To many more @OsmanticAI x @NVIDIAAI collaborations :)

Profilbild von NVIDIA RTX Spark
NVIDIA RTX Sparkvor 10 Tagen

@MTSlive @Dell Learn more about DGX Station: Check out the full podcast here:

Profilbild von Dell Technologies
Dell Technologiesvor 10 Tagen

@TheAhmadOsman @MTSlive Okay, thousands of tokens per second running locally will get our attention. 👀 Dell Pro Max + NVIDIA GB300 putting in work.

Profilbild von am.will
am.willvor 10 Tagen

@TheAhmadOsman @MTSlive @Dell Ahmad has been telling people to buy Nvidia GPUs for over two years now. NVDA Aug 27, 2024 = $124 $NVDA Today = $220 Coincidence? I think not.

Profilbild von Nexqor
Nexqorvor 10 Tagen

@TheAhmadOsman @MTSlive @Dell "locally" on a $40K workstation is a stretch of the word

Profilbild von sophia dew
sophia dewvor 10 Tagen

@TheAhmadOsman @MTSlive @Dell the dgx makes a great guest

Profilbild von Wbackdown
Wbackdownvor 10 Tagen

@sophiadew @TheAhmadOsman @MTSlive @Dell Damn I want one of these in Australia so bad!

Profilbild von Eirin Yagokoro🏳️‍🌈🏳️‍⚧️
Eirin Yagokoro🏳️‍🌈🏳️‍⚧️vor 10 Tagen

@TheAhmadOsman @MTSlive @Dell Looks like a Alienware gaming pc chase

Profilbild von Frank
Frankvor 10 Tagen

@TheAhmadOsman @MTSlive @Dell I'm gonna need one of these shipped pretty soon @NVIDIAAI please hurry

Profilbild von ఏది అయితే ఏంటి
ఏది అయితే ఏంటిvor 10 Tagen

give me one ..... will rule the world

Profilbild von Simon
Simonvor 10 Tagen

@TheAhmadOsman @MTSlive @Dell ...now make it actually affordable.

Ähnliche Videos

We got Unsloth AI a DGX Station! @DanielHanChen and Nader Khalil🍊 checked out Unsloth’s new Dell Technologies Pro Max with GB300 and talked about what comes next: support for more models, faster quantization, and more efficient reinforcement learning.
1:07

We got Unsloth AI a DGX Station! @DanielHanChen and Nader Khalil🍊 checked out Unsloth’s new Dell Technologies Pro Max with GB300 and talked about what comes next: support for more models, faster quantization, and more efficient reinforcement learning.

NVIDIA RTX Spark

23,678 Aufrufe • vor 4 Tagen

.NVIDIA hand delivered a pre-production unit of the Dell Technologies Pro Max with GB300 to my house. 100lbs beast with 750GB+ of unified memory to power the best open-source models in the world. What should I test first?
1:01

.NVIDIA hand delivered a pre-production unit of the Dell Technologies Pro Max with GB300 to my house. 100lbs beast with 750GB+ of unified memory to power the best open-source models in the world. What should I test first?

Matthew Berman

255,703 Aufrufe • vor 6 Monaten

Watch Gemma-4-26B running 18 concurrent sessions on a single NVIDIA AI DGX Spark — delivering a cumulative 300 tokens per second. 🔥
0:53

Watch Gemma-4-26B running 18 concurrent sessions on a single NVIDIA AI DGX Spark — delivering a cumulative 300 tokens per second. 🔥

Mia

23,211 Aufrufe • vor 2 Monaten

It's been an amazing week for open models running on NVIDIA Local AI systems! 👀 Here's a few you’ll want to know about, all ready to run locally on NVIDIA RTX, DGX Spark, DGX Station, and Jetson.
1:30

It's been an amazing week for open models running on NVIDIA Local AI systems! 👀 Here's a few you’ll want to know about, all ready to run locally on NVIDIA RTX, DGX Spark, DGX Station, and Jetson.

NVIDIA RTX Spark

60,708 Aufrufe • vor 1 Monat

🚨 BIG BREAKING Dell Technologies, with NxtGen AI, will build India’s LARGEST AI factory powered by 4,000+ NVIDIA Blackwell GPUs 🔥
0:56

🚨 BIG BREAKING Dell Technologies, with NxtGen AI, will build India’s LARGEST AI factory powered by 4,000+ NVIDIA Blackwell GPUs 🔥

Megh Updates 🚨™

62,872 Aufrufe • vor 8 Monaten

Running GLM-4.7-Flash with OpenCode locally on M4 Max MacBook Pro. 4-bit model runs at 82 tok/sec. Prefill will get ~4x faster with M5 Max MacBook Pro (~28 Jan). EXO will also support disaggregating prefill and decode across devices, e.g. DGX Spark.
0:43

Running GLM-4.7-Flash with OpenCode locally on M4 Max MacBook Pro. 4-bit model runs at 82 tok/sec. Prefill will get ~4x faster with M5 Max MacBook Pro (~28 Jan). EXO will also support disaggregating prefill and decode across devices, e.g. DGX Spark.

Alex Cheema

128,404 Aufrufe • vor 8 Monaten

image → 3D generation. a prompt is gently refined with Nemotron → FLUX paints a reference image → TRELLIS reconstructs a textured 3D mesh, running locally on an NVIDIA AI DGX Spark. quiet, local, always on.
0:43

image → 3D generation. a prompt is gently refined with Nemotron → FLUX paints a reference image → TRELLIS reconstructs a textured 3D mesh, running locally on an NVIDIA AI DGX Spark. quiet, local, always on.

three.ws

34,487 Aufrufe • vor 3 Monaten

We are getting 2 new devices from NVIDIA and Microsoft: 1. The DGX Station, with GB300 superchip and up to 748GB of memory. 2. The RTX Spark laptop, with 1 petaflop of AI performance and 128GB of unified memory. The hardware here is pretty bonkers! Think about it this way:
4:07

We are getting 2 new devices from NVIDIA and Microsoft: 1. The DGX Station, with GB300 superchip and up to 748GB of memory. 2. The RTX Spark laptop, with 1 petaflop of AI performance and 128GB of unified memory. The hardware here is pretty bonkers! Think about it this way:

Santiago

15,307 Aufrufe • vor 3 Monaten

So cool!! I'm running NVIDIA's NemoClaw with Qwen3.5-27B entirely locally via Telegram. No API costs, no data being sent to anyone NemoClaw is a security sandbox built on top of OpenClaw🦞 that lets you restrict the files and networks your lobster can access. I'm running the 4-bit GGUF via llama cpp on a DGX Spark. It's running pretty smoothly at 9 tokens per second! The future might be local :)
0:56

So cool!! I'm running NVIDIA's NemoClaw with Qwen3.5-27B entirely locally via Telegram. No API costs, no data being sent to anyone NemoClaw is a security sandbox built on top of OpenClaw🦞 that lets you restrict the files and networks your lobster can access. I'm running the 4-bit GGUF via llama cpp on a DGX Spark. It's running pretty smoothly at 9 tokens per second! The future might be local :)

Niels Rogge

209,499 Aufrufe • vor 6 Monaten

The #NVIDIAVeraRubin platform consists of five rack-scale systems for AI agents with a supply chain spanning over 350 factory sites across 30 countries with millions square feet of factory floor space.​ Vera Rubin is in full production, co-designed with NVIDIA DSX and DSX MaxLPS to deliver the lowest token cost and maximum tokens per watt.​ Congratulations to our partners who have their engineering racks up and running: CoreWeave, Dell Technologies, Microsoft, and Oracle Cloud.
1:14

The #NVIDIAVeraRubin platform consists of five rack-scale systems for AI agents with a supply chain spanning over 350 factory sites across 30 countries with millions square feet of factory floor space.​ Vera Rubin is in full production, co-designed with NVIDIA DSX and DSX MaxLPS to deliver the lowest token cost and maximum tokens per watt.​ Congratulations to our partners who have their engineering racks up and running: CoreWeave, Dell Technologies, Microsoft, and Oracle Cloud.

NVIDIA AI Infrastructure

16,701 Aufrufe • vor 2 Monaten

This afternoon I picked up a new Nvidia DGX Spark computer with the goal of trying to run Gemma 4 31b (4bit) on it locally as a server. Just 1.5 hours later, it’s working! Using Open WebUI on my MacBook as the interface and it’s connecting to my DGX Spark running as a Gemma 4 server.
0:46

This afternoon I picked up a new Nvidia DGX Spark computer with the goal of trying to run Gemma 4 31b (4bit) on it locally as a server. Just 1.5 hours later, it’s working! Using Open WebUI on my MacBook as the interface and it’s connecting to my DGX Spark running as a Gemma 4 server.

Dave Lee

140,876 Aufrufe • vor 5 Monaten

WebGPU is INSANE! 🤯 Here's a 24B parameter model running locally in a web browser, at a blazing ~50 tokens/second on my M4 Max. ⚡️ It's the largest model we've ever run with Transformers.js... and we're not stopping here. Big announcement soon.
1:05

WebGPU is INSANE! 🤯 Here's a 24B parameter model running locally in a web browser, at a blazing ~50 tokens/second on my M4 Max. ⚡️ It's the largest model we've ever run with Transformers.js... and we're not stopping here. Big announcement soon.

Xenova

36,251 Aufrufe • vor 6 Monaten

Intelligence at 1000 tokens per second, right in your terminal. Now available with SWE-1.6 Fast, powered by Cerebras. We're giving the first 100 people who respond a free month of Max to try it out.
0:31

Intelligence at 1000 tokens per second, right in your terminal. Now available with SWE-1.6 Fast, powered by Cerebras. We're giving the first 100 people who respond a free month of Max to try it out.

Cognition

289,189 Aufrufe • vor 4 Monaten

Nemotron-3-Nano-Omni-30B-A3B smashing 80 concurrent sessions on a single NVIDIA AI DGX Spark! 🔥 256k context. MTP enabled. All sessions running completely different prompts. ~800 tokens/s cumulative 🤯 Video starts slow but goes hard — watch till the end!
1:30

Nemotron-3-Nano-Omni-30B-A3B smashing 80 concurrent sessions on a single NVIDIA AI DGX Spark! 🔥 256k context. MTP enabled. All sessions running completely different prompts. ~800 tokens/s cumulative 🤯 Video starts slow but goes hard — watch till the end!

Mia

22,853 Aufrufe • vor 2 Monaten

📣 Get a first look at the NVIDIA Photonics co-packaged optics switch with Lambda. At NVIDIA GB300 NVL72 scale, the network doesn't just move data between GPUs — it determines how fast your cluster thinks. Co-packaged optics cut switch power, reduce failure points, and deliver more tokens per watt. Here's what that looks like in practice. ➡️
0:29

📣 Get a first look at the NVIDIA Photonics co-packaged optics switch with Lambda. At NVIDIA GB300 NVL72 scale, the network doesn't just move data between GPUs — it determines how fast your cluster thinks. Co-packaged optics cut switch power, reduce failure points, and deliver more tokens per watt. Here's what that looks like in practice. ➡️

NVIDIA AI Infrastructure

84,302 Aufrufe • vor 3 Monaten

Running Llama-3-70B at home with exo intern Combines the compute of all these devices to make one big GPU: - iPhone 15 Pro Max - iPad Pro M4 - Galaxy S24 Ultra - MacBook Pro M2 and M3 Pro - 2 x MSI NVIDIA GeForce RTX 4090 SUPRIM Code is open source 👇
0:21

Running Llama-3-70B at home with exo intern Combines the compute of all these devices to make one big GPU: - iPhone 15 Pro Max - iPad Pro M4 - Galaxy S24 Ultra - MacBook Pro M2 and M3 Pro - 2 x MSI NVIDIA GeForce RTX 4090 SUPRIM Code is open source 👇

Alex Cheema

197,476 Aufrufe • vor 2 Jahren

Paid Program with Dell Technologies and NVIDIA: “A lot comes down to the amount of data you’re able to train on.” Deepgram’s VP of Engineering Kris Efland explains why a well-designed technology infrastructure opens the door to innovation in voice AI.
0:23

Paid Program with Dell Technologies and NVIDIA: “A lot comes down to the amount of data you’re able to train on.” Deepgram’s VP of Engineering Kris Efland explains why a well-designed technology infrastructure opens the door to innovation in voice AI.

Custom Content from WSJ

22,561 Aufrufe • vor 2 Monaten

This is from my conversation with a Former $NVDA Director. If you want more TOKENS per SECOND because you are limited by POWER, you buy the next $NVDA generation. - Limited to 100 MW: $NVDA H100 = 300M tokens/second - Limited to 100 MW: $NVDA GB200 NVL72 = 12B tokens/second
2:22

This is from my conversation with a Former $NVDA Director. If you want more TOKENS per SECOND because you are limited by POWER, you buy the next $NVDA generation. - Limited to 100 MW: $NVDA H100 = 300M tokens/second - Limited to 100 MW: $NVDA GB200 NVL72 = 12B tokens/second

Rihard Jarc

57,622 Aufrufe • vor 1 Jahr

What does it take to run 3, 5, or even 10 concurrent instances of Gemma 4 locally? We've open-sourced a demo letting you run multiple models side-by-side on your hardware. Gemma 4 26B A4B easily runs 10+ concurrent requests on a MacBook Pro M4 Max at 18 tokens/sec per request.
0:48

What does it take to run 3, 5, or even 10 concurrent instances of Gemma 4 locally? We've open-sourced a demo letting you run multiple models side-by-side on your hardware. Gemma 4 26B A4B easily runs 10+ concurrent requests on a MacBook Pro M4 Max at 18 tokens/sec per request.

Google Gemma

915,024 Aufrufe • vor 5 Monaten