Company Serves 40 People with Local AI on 4x 6000 Pro GPUs

A company built a local AI server with 4x RTX 6000 Blackwell MaxQ GPUs, 384GB RAM, and an AMD EPYC CPU to serve 40 people, costing about €55k. Models include DeepSeek V4 Flash, Qwen 3.8 27B, and K2-Horizon 7B.

• China proposes export controls on 23 AI technologies2026-10-16
• Reflection AI to release US open-weight model to rival DeepSeek and Qwen2026-10-05
• From one 3090 to 20 DGX Sparks for local LLMs2026-10-04
• Balance of Power in Open Models: Chinese Firms Lead Open-Weight2026-09-23
• Yandex Releases 80B AliceAI Foundation Model2026-09-22