Topic

Local inference

Running language models on my own hardware instead of an API. 4 of 22 pieces.

The Better Model That Wouldn't Fit: Qwen 3.8 27B on a 32 GB Arc Pro B70

AI · Local inference · Home lab

Oct 22, 2026
My Qwen 3.8 Flash Next on Strata Got 40% Slower Overnight, and It Wasn't the GPU

AI · Local inference · Home lab

Oct 22, 2026
Building Jarvis: A Local Voice Assistant with Android and Hermes

AI · Agents · Local inference · Home lab

Oct 6, 2026
Deploying Qwen on Intel Arc with vLLM and DFlash2

AI · Local inference · Home lab

Oct 6, 2026