The Morning Dev

Only the news worth knowing

‹
 
  • AAPL 344.17 ▼ 1.53%
  • MSFT 535.93 ▼ 3.58%
  • NVDA 181.60 ▼ 9.26%
  • GOOGL 282.57 ▼ 2.20%
  • AMZN 260.21 ▼ 2.19%
  • META 605.08 ▼ 3.96%
  • TSLA 343.69 ▼ 10.77%
  • AVGO 291.53 ▼ 10.43%
  • TSM 353.10 ▼ 10.78%
  • ORCL 115.16 ▼ 6.93%
  • AMD 404.40 ▼ 17.26%
  • NFLX 65.56 ▼ 1.25%
  • CRM 222.41 ▼ 2.07%
  • ADBE 246.44 ▼ 0.82%
  • INTC 52.25 ▼ 10.33%
  • IBM 247.11 ▼ 2.84%
  • PLTR 154.99 ▼ 9.73%
  • SNOW 269.54 ▼ 7.25%
  • NET 244.51 ▼ 8.28%
  • SAP 243.53 ▲ 1.45%

Watch · Networking, Linux, homelab

local AI's biggest problem... they solved it?

NetworkChuck

Watch on YouTube ↗

Chapters

  1. 0:00The first Wi-Fi GPU: an RTX 5090 my laptop thinks is its own
  2. 0:38What WiCi One is, and what's inside the box
  3. 2:15Why Wi-Fi should be way too slow for a GPU
  4. 4:37The WiCi protocol: how they made the game and GPU stop talking so much
  5. 5:36From Tencent cloud gaming to a wireless GPU
  6. 6:05The two problems holding local AI back
  7. 7:32Why you can't run frontier-size AI models at home
  8. 9:57The math on running a 750 billion parameter model
  9. 11:59Mixture of experts, explained with badminton
  10. 13:50The four tricks that make DeepSeek V4.1 Flash usable on 32 GB of VRAM
  11. 15:16Running DeepSeek V4.1 Flash live on WiCi One
  12. 17:36Why GPUs don't like to share
  13. 19:41Testing WiCi's scheduler: switching AI models with and without it
  14. 21:06The family GPU: my verdict, pricing and shipping
  15. 22:18A prayer for you
Show the full video description ›

Get $600 off either edition of WiCi One, the first wireless GPU, using my link: https://ntck.co/wici_gpu I ran DeepSeek V4.1 Flash, a 750 billion parameter model that normally needs over 500 GB of memory, on a box with only 32 GB of VRAM. Over Wi-Fi. By the numbers that shouldn't work. The box is WiCi One, a GPU every device in your house can share. In this video you'll learn why big local models don't fit on consumer GPUs, and how WiCi got one running anyway. ☕☕ COFFEE and MERCH: https://ntck.co/coffee *Sponsored by WiCi RESOURCES / LINKS: 🖥️ WiCi One (RTX 5060 Ti edition, or the RTX 5090 edition I tested), $600 off with my link: https://ntck.co/wici_gpu 🧠 InferSSD, WiCi's open-source engine for running models bigger than your VRAM off an SSD: https://github.com/wici-ai/inferssd 🤖 DeepSeek V4.1 Flash on Hugging Face: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash 🎨 Lovart (AI image and video generation): https://www.lovart.ai 🎨 Figma: https://www.figma.com Figma and Lovart are cloud apps. For this demo, their AI generation requests were redirected to a model running locally on WiCi One. TIMESTAMPS: 0:00 - The first Wi-Fi GPU: an RTX 5090 my laptop thinks is its own 0:38 - What WiCi One is, and what's inside the box 2:15 - Why Wi-Fi should be way too slow for a GPU 4:37 - The WiCi protocol: how they made the game and GPU stop talking so much 5:36 - From Tencent cloud gaming to a wireless GPU 6:05 - The two problems holding local AI back 7:32 - Why you can't run frontier-size AI models at home 9:57 - The math on running a 750 billion parameter model 11:59 - Mixture of experts, explained with badminton 13:50 - The four tricks that make DeepSeek V4.1 Flash usable on 32 GB of VRAM 15:16 - Running DeepSeek V4.1 Flash live on WiCi One 17:36 - Why GPUs don't like to share 19:41 - Testing WiCi's scheduler: switching AI models with and without it 21:06 - The family GPU: my verdict, pricing and shipping 22:18 - A prayer for you **Sponsored by WiCi SUPPORT NETWORKCHUCK: ☕☕ COFFEE and MERCH: https://ntck.co/coffee READY TO LEARN?? 🔥🔥Join the NetworkChuck Academy!: https://ntck.co/NCAcademy 📚 CCNA Course: https://ntck.co/ccna FOLLOW ME EVERYWHERE: Instagram: https://www.instagram.com/networkchuck/ X/Twitter: https://x.com/networkchuck Facebook: https://www.facebook.com/NetworkChuck/ Join the Discord server: https://ntck.co/discord Some links in this description are affiliate links. If you buy through them, I may earn a small commission

More from NetworkChuck

More to watch