הבא בתור
Ethernet is DEAD?? Mac Studio is 100x FASTER!! 34 דק׳ 
NVIDIA's New Free AI - A Gift To Humanity 8 דק׳ 
IBM’s mainframe chip collab, NVIDIA’s Poolside deal & Ox Alpha’s reveal 31 דק׳ 
STALKER 2, GTA 6, Клоунада PlayStation, DLSS 5 Слоп, Far Cry 7, ПЗДЦ Game Pass Wolverine The Witcher 44 דק׳ 
PRAGMATA - This Ending Hit Hard 179 דק׳ 
This GPU can be Hacked to Unlock Secret Memory 20 דק׳ 
My Son Needs a New Laptop 20 דק׳ 
How To Manage Token Costs While Keeping Agentic Goals On Track 5 דק׳ 
KÖK BÖRÜ | AI Animated Short Film | Higgsfield Originals (2026) 16 דק׳ 
We Built the BEST PC 14 דק׳ 
PRAGMATA Walkthrough Gameplay Part 2 - GIGANTIC BOT BOSS FIGHT (FULL GAME) 94 דק׳ 
testing Wii Bowling in the shower 1 דק׳ 
JAGUAR F TYPE R AWD is V8 GLORY on the AUTOBAHN!! 
470HP Audi RS3 8V // 0-100 100-200 & MILLTEK SOUND 9 דק׳ 
Turning children's glue into drinkable alcohol 62 דק׳ 
I Tested 47 Sony Cameras – These Are My Favorite! 18 דק׳ 
508HP Porsche 944 TURBO // POV on AUTOBAHN 9 דק׳ 
I Built a FREE App That Runs Your Entire Business 28 דק׳ 
The Case For Data Centers In Space 37 דק׳ 
The DJI Pocket 4 & 4P Just Got a BIG Update! 9 דק׳ 
One Piece Season 3 #shorts #onepiece #onepieceseason3 #netflix 1 דק׳ 
Bashenga: The First Black Panther (2027) John Boyega & Tyrese Gibson 9 דק׳ 
Ads in Video Games 20 דק׳ 
The most interesting "hack" in history... 5 דק׳ 
Insta360 X6: The Vlogging Camera I Didn't Expect! 16 דק׳ 
You're only 6 months away from living your dream life 31 דק׳ 
Plasma Globe is a ⚡Shocking⚡🔥Fire Hazard🔥 12 דק׳ 
Insta360 X6 vs Luna Ultra: Best Vlogging Camera? 20 דק׳ 
Can Mr Bean's Mini Beat Declan's Fancy SUV? 🚗 | Mr Bean Animated Season 3 | Funny Clips | Mr Bean 24 דק׳ 
The Road to 3 Million Views🚀 1 דק׳ 
🌈Rainbow food compilation pick your favorite color | That Little Puff 10 דק׳ 
Ferrari's Electric Car Looks Like... 2 דק׳ 
A 1,000,000,000 Particle Simulation! 🌊 1 דק׳ 
Living by Power Lines #science #electrical #cancer 2 דק׳ 
Fighting Electrical Fire by AFCI 16 דק׳ 
Can a PS5 cook an egg? 1 דק׳ 
Genius idea... Bad execution 1 דק׳ 
Claude AI Failed 650 Times…Then Beat The Human Record 5 דק׳ 
The Truth About the Bezelless Concept Phone 7 דק׳ 
$10,000 Power Washer vs Fruit 1 דק׳ 
Meet the Pets - Yvonne's Three Chickens 16 דק׳ 
7 killer website features 1 דק׳ 
Nuclear Egg (LATITY-015) 14 דק׳ 
my browser, my paste 1 דק׳ 
Can your iPhone see the back of your head? 1 דק׳ 
Web 1.0-beta 1 דק׳ 
Scientists Found A Better Language For AI Agents 7 דק׳ 
I tested every new Apple Product! 15 דק׳ 
Google Pixel 11 Hands on - The Phone Crisis Begins. 14 דק׳ 
Adding Recoil to My Mouse was a lot Harder than I Thought... 19 דק׳ 
This or the iPhone? 2 דק׳ 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