Vigyata.AI
Is this your channel?

DGX Spark? Nah-My Hal-9000 Dual GPU Rig Wins for Cheap A.I. and Gaming Power

352 views· 21 likes· 34:40· Nov 13, 2025

🛍️ Products Mentioned (2)

DGX Spark? Nah-My Hal-9000 Dual GPU Rig Wins for Cheap A.I. and Gaming Power We add a little bling to my Under $1000 Gaming/AI rig and compare it to the speed of the DGX Spark @ $4000 dollars. CREDITS: "Subscribe Button" by MrNumber112 https://youtu.be/Fps5vWgKdl0 Music I Use: https://www.bensound.com/free-music-for-videos License code: MS6H2K6QACHPUSXU Visit our sister channel Unkyjoe's Aquatics: https://www.youtube.com/channel/UCWHrQHkTZ1iACO8VxIXkBzw Thanks for watching! I hope you all enjoy... Join us on LBRY:https://lbry.tv/$/invite/@unkyjoesplayhouse:9 Facebook: https://www.facebook.com/UnkyjoesPlayhouse/ Twitter :https://twitter.com/ujplayhouse Email:unkyjoesplayhouse@gmail.com For PayPal or Patreon donations to Unkyjoe's Playhouse, please visit the "About" section on my channel. All cash donations are directly put back into Unkyjoe's Playhouse channel projects. I cannot respond to all emails, but give it a go! *PLEASE NOTE* I do not respond to YouTube or Google+ private messages. Please contact me via the official Facebook page or via my email address to get in touch.

About This Video

In this one I finally got tired of my old “AI powerhouse” case, so I swapped my Hal-9000 dual-purpose Gaming/AI rig into a new Nova Mesh SE 2.0 case I grabbed for about $60. You get to watch me do the full transplant—board in, cable wrangling, fan/LED controller hookups, drive mounting, and then the big moment: hit the power button and pray for no explosions. It boots, it lives, and yeah… it’s got bling. I still don’t really give a rat’s ass about LEDs, but if it’s going to be a powerhouse, why not make it look pretty? Then I walk through what’s actually inside this thing: an i5-10400, 64GB DDR4, a 4TB WD game drive, a 1–2TB NVMe, and the stars of the show—two RTX 3060s. I’m running Ollama on Windows and using Open WebUI as the front end from a Proxmox LXC container (Proxmox all the things), pointing it back to the Windows box for models and inferencing. Out of the box it split the load across both GPUs and I’m seeing solid token speeds, even while I’m also generating images in Invoke. Finally, I talk about the DGX Spark hype and why, for my needs, a sub-$1000 DIY dual-GPU rig makes way more sense right now than dropping around $4K on something that looks slower in the reviews I watched.

Frequently Asked Questions

🎬 More from Unkyjoe's Playhouse