> don't mix and match GPUs
> separate 3090s rig
> the mobo you already got would cause a bottleneck for 2x GPUs in all cases
> you might wanna return mobo and upgrade to an epyc/xeon/tr build, or just use it as it is for a single gpu
> processor/ram/(and partially mobos) are
AI HARDWARE
-
GPU Rig Configuration: Avoid Mixing 3090s and Bottleneck Issues
By
–
-
Running DeepSeek Locally: VRAM Requirements and Privacy
By
–
is there any site like this to download VRAM? i wanna run DeepSeek locally (for privacy reasons – don't wanna give my data to china)
-
Building AI System: GPU Hardware Budget and Configuration
By
–
what parts do you have so far? budget? one or more GPUs? and do you plan on adding more?
-
Stargate expansion: Five new sites with Oracle and SoftBank
By
–
We’re building 5 new Stargate sites with Oracle and SoftBank:
-
RTX 5090 Available at MSRP from Walmart
By
–
RTX 5090 at MSRP!!! sold and shipped by Walmart x.com/Matthewrogers/…
-
Building AI Infrastructure: Why You Should Invest in GPUs
By
–
My house has 33 GPUs > 21x RTX 3090s
> 4x RTX 4090s
> 4x RTX 5090s
> 4x Tenstorrent Blackhole p150a Before AGI arrives: > Acquire some GPUs
> Learn how LLMs work
> Don't get left behind These are investments that will pay dividends in the future Invest in yourself
Buy a GPU -
Oracle Stock Surges 36% on OpenAI Cloud and Nvidia GPU Deal
By
–
Ils jouent un jeu dangereux : 1. Oracle annonce qu’OpenAI s’est engagé à dépenser 300 milliards de dollars pour du cloud → l’action Oracle bondit de 36 % (meilleure journée depuis 1992). 2. Oracle fonctionne sur des GPU Nvidia → doit acheter des milliards de puces à Nvidia.
-
Groq Welcomes TinyTPU Team to Company
By
–
Stoked to welcome the TinyTPU team to Groq @evanliin
, @XanderChin
, @suryasure05
, @kennykgguo How it started How it's going -
Local LLM Network Setup: Windows RTX 5090 to MacBook Pro
By
–
What app should I install on my Windows RTX 5090 PC so I can have a local network LLM on my MacBook Pro on same network? And can I use it on Cursor, no right?