-
AI server 3090
May 2026 picks: 2x RTX 3090 (48GB) for the dense-model workhorse; 2x RTX 5060 Ti 16GB (32GB) for budget MoE with --cpu-moe; 2x RTX 2080 Ti 22GB modded for value (Qwen 3. 6 27B at 38 tok/s); 1x 3090 + 1x 4090 for mixed-card pipeline parallelism. cpp and Ollama handle. Want to build a GPU home server for running quantized models? Here's some tips and tricks for setting up the server. RTX 3090: Two RTX 3090s with NVLink are a common choice for running large AI models. Previously I have built one but only for mining where those GPUs were connected via PCIE x1 risers. 0 x16 so the thing looks slightly different. Building a full DIY rig is a high base cost with inflation with every new recent dual slot capable motherboard checking in above $100. AI from The Basement: My latest side project, a dedicated LLM server powered by 8x RTX 3090 Graphic Cards, boasting a total of 192GB of VRAM. This blogpost was originally posted on my LinkedIn profile in July 2024. Backstory: Sometime in. A 70B model that can't fit on one 24GB card runs at 16-21 tok/s across dual RTX 3090s. You need server-grade platforms.
[PDF Version]
-
Where are AI servers typically set up
The location of AI data centers is determined by several factors including network connectivity, energy costs, data privacy regulations, and proximity to markets. AI data centers are generally spread across major global regions to ensure accessibility, compliance, and operational. An AI data center is a specialized data center facility designed for the computationally intensive tasks of training and running inference for artificial intelligence (AI) and machine learning models. Unlike general-purpose data centers, they are optimized for the parallel processing demands of AI. These data centers are equipped with powerful servers and cloud infrastructure to support AI tasks like machine learning, deep learning, and data analytics. That's the job of an AI server—a custom-built system that keeps AI applications fast, scalable, and efficient. Some of these operations involve deep learning, image recognition, and natural language processing.
[PDF Version]