Supermicro ARS-511GD-NB-LCC: DGX Station GB300 Inside

By Maximilian Batz | 2026-08-29

The Supermicro Super AI Station ARS-511GD-NB-LCC is Supermicro’s implementation of the NVIDIA DGX Station GB300 platform, in a 5U tower. We photographed one with the side panel removed at ISC 2026, including the liquid-cooling loop that most published material only shows as a rendering. Below are verified specifications, what the interior looks like, and how…

Weiterlesen

Gigabyte W775-V10-L01: DGX Station GB300 Teardown

By Maximilian Batz | 2026-08-29
Gigabyte tower chassis with gold-toned ribbed side panel on display — Gigabyte W775-V10-L01 NVIDIA DGX Station GB300

At ISC 2026 we got a Gigabyte W775-V10-L01 with its side panel off, and photographed it properly. It is one of the first deskside implementations of the NVIDIA DGX Station GB300 platform, and there is very little published photography of one opened up. Below are the verified specifications, what the interior actually looks like, and…

Weiterlesen

NVIDIA Education (EDU) discount for DGX Station GB300 in 2026

By Maximilian Batz | 2026-07-31

NVIDIA offers education discounts for different NVIDIA hardware products, and different subscription services. How high is the NVIDIA Education (EDU) discount for the DGX Station GB300? NVIDIA is currently finalizing details on the discount levels for the DGX Station with the GB300 superchip. We are expecting final information to be released around 10th to 15th…

Weiterlesen

NVIDIA DGX Station GB300 FAQs

By Maximilian Batz | 2026-07-04

How fast is the NVIDIA DGX Station GB300? Our first customer for the DGX Station GB300 allowed us to share this screenshot. It shows the performance of DeepSeek-V4-Flash-NVFP4 and Qwen2.5-Coder-32B-Instruct. These models fit comfortably into the HBM3e VRAM. DeepSeek-V4-Flash-NVFP4 achieves around 159 output token/s, and Qwen2.5-Coder-32B-Instruct around 70 – 73 output token/s. Which LLM models…

Weiterlesen