Következő
Ethernet is DEAD?? Mac Studio is 100x FASTER!! 34 perc 
Jensen Huang: The Mindset That Built NVIDIA 49 perc 
This GPU can be Hacked to Unlock Secret Memory 20 perc 
DLSS 5 is NOT What We Expected 19 perc 
Open Models Change The Economics of AI 58 perc 
Lessons From Training Composer At Cursor And Building Meta/Nvidia Compute Clusters | YC Paper Club 77 perc 
This AI Supercomputer can fit on your desk... 24 perc 
AI News: The AI Agent Race Just Exploded 35 perc 
We Built the BEST PC 14 perc 
GTA 6 ПЗДЦ, The Witcher 4, METRO 2039, Успіх STALKER 2, Провал Sony, Days Gone, Клоуни IGN, Rockstar 35 perc 
PRAGMATA - This Ending Hit Hard 179 perc 
Testing What Happens If You Jump On A Moving Train 19 perc 
Attacked by ZOMBIES in Hamburg! 🇩🇪 39 perc 
BENTLEY CONTINENTAL GTC SPEED // TOP SPEED on AUTOBAHN 
ENGINE & ACTIVE AERO VIEW of a LAMBORGHINI REVUELTO at TOP SPEED 
I Tried Building My Own Space Satellite 25 perc 
BMW X5M Competition F95 // MHD STAGE 1 & XHP // REVIEW on AUTOBAHN 11 perc 
Trying To Solve The Biggest AI Problem 21 perc 
ALPINA E36 B3 3.2 // TOP SPEED on AUTOBAHN 
1989 BMW 750il E32 // 0-100 100-200 TOP SPEED POV & SOUND 8 perc 
FERRARI GTC4LUSSO T NOVITEC // 300KM/H on AUTOBAHN 9 perc 
LAST TO LEAVE THE ISLAND 68 perc 
What Is Digital Sovereignty? AI, Data & Control Explained 10 perc 
Google DeepMind CEO Loves Hard Questions 🙂 1 perc 
Bond 26 (2027) Henry Cavill & Margot Robbie 9 perc 
I Tested 47 Sony Cameras – These Are My Favorite! 18 perc 
Why Does AI Need Access to the Web? 20 perc 
Luna Pro 4K Vertical Video Is a HUGE Upgrade! 1 perc 
I Promise you this is NOT Stupid 10 perc 
Bankrupt - iRobot (Roomba Vacuum) 20 perc 
What should security leaders do with AI? They don’t know. 30 perc 
Bluey Phone Review 5 perc 
I tested phones that shouldn’t EXIST 23 perc 
Canada is Beating US in Electrical Upkeep! 25 perc 
Violent iPhone Repair 20 perc 
DeepMind Just Changed How AI Sees The World 6 perc 
$1 vs $100 LED Gadgets 1 perc 
Antigravity A1: A New Take on Drones! 11 perc 
iOS 27 Hands-On: Top 5 New Features! 16 perc 
5 Pros and Cons of Apple's New Foldable Phone 2 perc 
$1000 RC Car Battle 1 perc 
Science Mutilation by History Channel 18 perc 
Another DeepSeek Moment Has Arrived 5 perc 
I Investigated IKEA’s Suspiciously Cheap Tech 18 perc 
real HTML programmers debug in 3D 1 perc 
Plasma Speaker DIY (AM Demodulator) 11 perc 
Apple just Copied Microsoft’s Worst Idea - iPhone Duo, Airpods 5, iPhone 18 Pro & More 19 perc 
The Best TINY Tech on the Internet! 20 perc 
Current Kills or Voltage #electricity #science #experiment 2 perc 
Genius idea... Bad execution 1 perc 
Fastest GPU on the Planet 1 perc Hey…just try Twingate….you'll never look at VPN the same: https://ntck.co/twingate-networkchuck I built another AI supercomputer with 4 Mac Studios... but this time it actually works. Earlier this year, I clustered 5 Mac Studios and it was 91% SLOWER. Everyone said clustering was stupid. But Apple just dropped a software update that changes everything - RDMA over Thunderbolt 5. Latency dropped from 300 microseconds to 3 microseconds. Now we're running trillion-parameter models locally at speeds that actually make sense. 🔥🔥Join the NetworkChuck Academy!: https://ntck.co/NCAcademy RESOURCES / LINKS: Docs/walkthrough: https://github.com/theNetworkChuck/mac-studio-cluster Exo Labs: https://github.com/exo-explore/exo MLX (Apple's ML Framework): https://github.com/ml-explore/mlx My First Cluster Video (the failure): https://youtu.be/Ju0ndy2kwlw RDMA Networking Explained: https://youtu.be/fb69FyW2KLk TIMESTAMPS: 0:00 - The $50,000 AI Supercomputer 0:53 - What Apple Changed 3:05 - Connecting the Cluster 4:17 - Pipeline vs Tensor Parallelism 7:52 - RDMA: The 100x Latency Fix 10:02 - Twingate (Sponsor) 11:39 - Exo Labs is BACK 14:42 - Single Node vs Cluster Testing 17:58 - Qwen 3 Coder 480B Testing 19:03 - Kimi K2 (1 Trillion Parameters) 21:09 - Stacking Multiple Models 25:22 - Real Apps: Open WebUI + Xcode 27:57 - Final Thoughts 28:47 - How MLX Makes This Possible **Sponsored by Twingate THE SPECS: • 4x Mac Studio M4 Ultra (512GB RAM each) • 2TB unified memory / 320 GPU cores / 32TB storage • $50,000 (vs $780,000+ for equivalent NVIDIA H100s) THE RESULTS: • Llama 3.3 70B: 16 tok/s (3x faster than before) • Kimi K2 (1T params): 28 tok/s • DeepSeek V3.1 671B: 27 tok/s • Qwen 3 Coder 480B: 40 tok/s SUPPORT NETWORKCHUCK --------------------------------------------------- 🎓🎓 Sign up for NetworkChuck Academy: https://ntck.co/NCAcademy ☕☕ COFFEE and MERCH: https://ntck.co/coffee 🌐🌐 Use the MOST SECURE Web Browser, NetworkChuck Cloud Browser: https://browser.networkchuck.com/ 🧠🧠 Use n8n, my favorite automation tool: https://ntck.co/n8n 🆘🆘 NEED HELP?? Join the Discord Server: https://discord.gg/networkchuck STUDY WITH ME on Twitch: https://bit.ly/nc_twitch READY TO LEARN?? --------------------------------------------------- -Sign up for NetworkChuck Academy: https://ntck.co/NCAcademy -Get your CCNA: https://bit.ly/nc-ccna FOLLOW ME EVERYWHERE --------------------------------------------------- Instagram: https://www.instagram.com/networkchuck/ Twitter: https://twitter.com/networkchuck Facebook: https://www.facebook.com/NetworkChuck/ Join the Discord server: http://bit.ly/nc-discord Do you want to know how I draw on the screen?? Go to https://ntck.co/EpicPen and use code NetworkChuck to get 20% off!! clustering works now. thank Apple and Exo Labs. # # # TAGS: mac studio cluster, ai supercomputer, local ai, rdma, exo labs, apple silicon, m4 ultra, unified memory, tensor parallelism, llm, kimi k2, deepseek, llama, mlx, thunderbolt 5, home lab ai, self hosted ai, 2tb ram, gpu cluster, apple ai
Packages published by the creator behind this video.
This creator has not set their rates yet. Send a request and we will pass it on — the price is agreed before anything is charged.
A recurring seat in my content. Subscribers enter a queue — or a random draw when there are more subscribers than slots — and appear in the video itself, in the credits, or in the description.
per month
Price on request
A guaranteed appearance of at least 10 seconds in my next video. Price depends on where in the runtime the insert lands.
Price on request
A guaranteed appearance of at least 10 seconds inside a Short cut from one of my existing videos.
one-off
Price on request