Built a Dual RTX 6000 Pro Rig for Local DeepSeek — Warns Against Influencer Build Hype
HankYeomans · x · 2026-09-04
With ChatGPT down, one user ran DeepSeek V4 MXFP4 locally on a self-built workstation (Threadripper PRO 9955WX, dual RTX 6000 Pro Max-Q, 8x RDIMM) to produce a build montage video: model response under a minute, with only MacBook rendering taking 10-15 min. Caveats: the WRX90E board locks you into pricey RDIMM-only memory, pure inference doesn't justify this spend — and beware influencer hype like "you need a Mac Mini for OpenClaw."
Related event: User Runs DeepSeek Locally on Dual RTX 6000s During ChatGPT Outage(2 posts)→
More from Infra
- 71% oppose, 261 moratoriums: US data center approvals are freezing over — shashib · 2026-09-04
- Micron explores near-GPU NAND flash to run bigger LLMs — giveen · 2026-09-04
- HPE Delivers Strong Q3 on AI Server Demand, Raises FY2026 Outlook — mattwbaker · 2026-09-04
- All Chromium Browsers Hit by Hard-to-Reproduce Data Loss Bug, Devs Say — uwukko · 2026-09-04
- Hundreds protest Scotland's datacentre boom, demanding pause on 20+ proposed projects — nordicinst · 2026-09-04
- Inference engines are an underexamined attack surface, self-hosting ops warned — JeremyCMorgan · 2026-09-04