by Kashish

I Tested Small Qwen Models for Real Business Workflows , Here’s What Actually Happened

TL;DR: Small Qwen models running locally on consumer hardware are already good enough for OCR automation, […]
read more
by Kashish

What Are Obliterated and Uncensored AI Models , And Why Enterprise Workflows Actually Care

“The problem isn’t safety. The problem is when safety layers can’t tell the difference between a […]
read more
by Kashish

Running Small Qwen Models on Consumer Hardware: RAM, Speed, and What Local AI Actually Feels Like

“The question isn’t whether small models are perfect. It’s whether they’re useful enough to build with.” […]
read more
by Kashish

Why Small Qwen Models Are Quietly Becoming the Most Exciting Thing in Local AI

“You don’t need a data center to run useful AI anymore. That changes everything.” I remember […]
read more