@0xSero: I had to reorganise my 6000s to get the 4 side by side. This motherboard (Asrock romed8-2t is a bit weird) I also got a…
Summary
A user shares their experience reorganizing four RX 6000 GPUs on an Asrock romed8-2t motherboard, discusses adding a UPS, and asks for recommendations to expand to eight GPUs with better cooling and a server rack.
View Cached Full Text
Cached at: 07/07/26, 09:38 PM
I had to reorganise my 6000s to get the 4 side by side. This motherboard (Asrock romed8-2t is a bit weird)
I also got a UPS to help protect against any power issues.
Im looking to upgrade mobo (ideally gen 5 and 8 slots) and a way to use ddr4 on gen 5 slots
Also better cooling, maybe water cooling? A server rack? What would you recommend?
Say I want to get to 8x 6000s at some point.
Similar Articles
@TheAhmadOsman: Hey my friend, cool setup. If 8x RTX PRO 6000s is the real goal, I’d treat it like a serious infra build, not a worksta…
Advice on building a high-end AI workstation with 8x RTX PRO 6000 GPUs, emphasizing proper infrastructure, cooling, and avoiding reuse of DDR4.
@barrowjoseph: https://x.com/barrowjoseph/status/2056417511826989310
A grad student shares their experience building a multi-GPU workstation with 4x3090 Ti running on a single US wall outlet, detailing constraints, power-limiting challenges, and component choices.
@0xSero: Rejoice fellow 6000 enjoyers. We have GLM at home
A turnkey Docker setup to serve the GLM-5.2-NVFP4-REAP-469B model on 4× RTX PRO 6000 Blackwell GPUs using vLLM, with detailed instructions and configuration options.
@Mayhem4Markets: I am so excited right now! My new motherboard just arrived. Got an @ASUS Pro WS W890SE-Sage SE. This thing is a beast. …
User expresses excitement over the arrival of an ASUS Pro WS W890SE-Sage SE motherboard for a high-end workstation build, including Intel Xeon processor and Nvidia RTX 6000 Pro Blackwell cards.
I accidentally crippled my 4x RTX 3090 LLM rig with a hidden PCIe 2.0 x4 slot and fixing it doubled Mistral 128B performance
A user discovered that a hidden PCIe 2.0 x4 electrical limitation on a Threadripper workstation board was crippling one of four RTX 3090s, causing poor multi-GPU LLM inference performance. Fixing the slot layout and switching to tensor split mode doubled Mistral 128B throughput from ~11 to ~24.7 tok/s.