月間参加
月額私のコンテンツの定期的な席。購読者はキューに入るか、枠よりも購読者が多い場合はランダム抽選で、ビデオ本体、クレジット、または説明に登場します。
月額
価格はお問い合わせ
次に再生
Ethernet is DEAD?? Mac Studio is 100x FASTER!! 34 分
AI News: OpenAI Absolutely Cooked This Week! 35 分
KÖK BÖRÜ | AI Animated Short Film | Higgsfield Originals (2026) 16 分
NVIDIA CEO Jensen Huang's Vision for the Future 64 分
AI News: The AI Agent Race Just Exploded 35 分
IBM’s mainframe chip collab, NVIDIA’s Poolside deal & Ox Alpha’s reveal 31 分
STALKER 2, GTA 6, Клоунада PlayStation, DLSS 5 Слоп, Far Cry 7, ПЗДЦ Game Pass Wolverine The Witcher 44 分
AI News: Microsoft Finally Reveals Their Plan! 31 分
AI News: OpenAI Made a Massive Move Against NVIDIA 30 分
IBM’s cloud collab, Meta’s Muse Glimmer & OpenAI’s upcoming Astra model 37 分
This Small AI Will Change Everything 4 分
CUPRA LEON ST VZ 333 // TOP SPEED on AUTOBAHN 9 分
630HP BMW X4M // REVIEW on AUTOBAHN
Corvette Z06 C8 // 313KMH REVIEW on AUTOBAHN
AUDI RS7 C8 // 0-287 1 分
Why Everyone Is Freaking Out About Fable 5 (Mythos) 21 分
GOT a BURGER with our BMW M4 F82 and DROVE the AUTOBAHN at NIGHT 13 分
Primitive Technology: Double water bellows 20 分
CORVETTE C8 Z06 8600RPM V8 SOUND 0-100 100-200 & TOP SPEED FLY BY on AUTOBAHN
TUNING my PORSCHE 992 CARRERA S with M Engineering! Stage 1 0-100 100-200 200-300 13 分
2026 Audi RS5 Avant B10 // TOP SPEED REVIEW on AUTOBAHN 12 分
The illusion of the ‘self’ | The Gray Area 43 分
Five things you need to know for the 2026 midterms | America, Actually 31 分
Why is getting bitten by a rabid animal so dangerous? - Charles Rupprecht 7 分
The Most Interesting Displays In The World! 16 分
Your Next Budget PC Upgrade is...Custom Watercooling?? 25 分
Zero Gravity Is Weirder Than You Think (Bonus Episode) 12 分
How do Maglev trains work? - Ning Zhao 7 分
We Took Our Food Delivery Man on His First Vacation 46 分
The shoes that broke walking 9 分
Data centers can’t win on Earth. How about in space? 2 分
New Alien Host Planet Just Dropped 1 分
Why Sagrada Familia Took 144 Years to Complete 25 分
Crazy New Machine Helps Us Find Aliens 1 分
The Best Car I've Ever Driven: McLaren W1 17 分
Why Does Antarctic Ice Look So Weird? 1 分
What's Hidden Under Antarctica? 19 分
The Shoe That Broke Running 16 分
These Earbuds have a World Record 1 分
I Tested Smartphones from Every Country 25 分
NASA's Plutonium Problem 2 分
Life finds a way... except here. #shorts #science #SciShow 1 分
The F-14 was designed for one reason 2 分
The Weird Orbit of the ISS 2 分
Editing Your DNA, with Nobel Prize Winner Dr. Jennifer Doudna 54 分
I tested Dream Tech with my Biggest Fans! 15 分
Humanity’s Real Plan to Stop This Asteroid (Feat. Mark Rober) 22 分
Meet the slow loris, the only venomous primate in existence - Stephanie A. Poindexter 6 分
The Real Reason We Should Revive Extinct Animals 16 分
The Dark Side of the World’s Lightest Structural Metal 16 分
Why men can’t get hard 9 分 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
このビデオのクリエイターが公開したパッケージ。
このクリエイターはまだ料金を設定していません。リクエストを送信してください — 何かが請求される前に価格が合意されます。
私のコンテンツの定期的な席。購読者はキューに入るか、枠よりも購読者が多い場合はランダム抽選で、ビデオ本体、クレジット、または説明に登場します。
月額
価格はお問い合わせ
次のビデオに10秒以上の保証出演。価格は挿入が作品のどこに配置されるかによります。
価格はお問い合わせ
既存のビデオからカットしたショート動画内に10秒以上の保証出演。
一回限り
価格はお問い合わせ