Local AI Speed Is Decided by Memory Bandwidth — Four Machines Measured
When you are thinking about running local AI ...
Trying Ornith-1.0 on Home Hardware — Measuring Speed and How Well It Reasons
I wanted to find out how far a code-focused l ...
OCuLink or Thunderbolt for an External GPU? I Measured Both With the Same Card | Mini PC eGPU Part 1
When you hang an external graphics card off a ...
The Mini PC Lid Would Not Close — I Tried Three M.2-to-OCuLink Adapters
A while back I wrote about pulling an OCuLink ...
I Want My Avatar to Emote While Wearing the Headset — What Do I Actually Buy for Face Tracking?
I wrote earlier about body tracking in VR — f ...
What the Intel Arc B580 Could and Could Not Do | Intel Arc B580 Local LLM Part 7
I put a 12GB Intel Arc B580 in next to the NV ...
What Happens If You Mix GPUs From Different Vendors? RTX 3090 + Intel Arc B580 Measured | Intel Arc B580 Local LLM Part 6
This desktop has an NVIDIA GeForce RTX 3090 ( ...
Six Local LLMs, Same Prompts: Speed, Japanese Output, Summarizing and Code
I run local LLMs on a machine with an RTX 309 ...
My Whole Local AI Workstation, Documented: Ubuntu + RTX 3090 + Ollama + ComfyUI
I built a workstation at home dedicated to lo ...
What Are AI Agents, Really? Four Types and Which Ones Run Locally (June 2026)
"AI agent" is a phrase I have been seeing eve ...









