Home Blog
We show you how you can run the 1.27TB Deepseek-R1 671B model at FP16, and even look at running it alongside VMs in your clusters
The new MLPerf Inference v5.0 results are out with new submissions for configurations from NVIDIA, Intel Xeon, and AMD Instinct MI325X
In our Dell Precision 3280 Compact review, we see how we got 128GB of memory, a 20GB NVIDIA GPU, RAID 0 SSDs, and 24 cores into a small PC
In our Supermicro SYS-112C-TN review, we see how this single-socket Intel Xeon 6 server performs and how it is designed differently
In the STH Q1 2025 Letter from the Editor, we go behind-the-scenes at STH and talk about what we have been working on
These Crucial 64GB DDR5-5600 SODIMMs come in pairs for 128GB in the kit allowing for more memory in mini PCs (and notebooks)
We take a look at SMT in 2025 and why the two threads per core regime is still dominant in the enterprise, perhaps becoming moreso
The NVIDIA Kyber midplane for the Rubin NVL576 generation is huge, requiring system design beyond traditional blade servers
For a long time, we have been focusing a lot on the hardware costs of new processors but missing the virtualization license costs. Part...
The NVIDIA DGX Station GB300 edition packs a 72 core Arm CPU, 800Gbps ConnectX-8 networking, a 288GB B300 GPU, and more