What secretly eats your local LLMs' speed as your context fills up - Part 2
So, we left in the previous chapter with some data and insights. This time we talk about the story...
Jul 4, 20264 min read0 reactions0 comments
Back to articles Jul 4, 2026 
Jun 4, 2026
Apr 7, 2026
Jul 22, 2025
Tag archive
#locallm
W
Jun 25, 2026What secretly eats your local LLMs' speed as your context fills up - Part 1
Did you ever notice that sometimes while you use a model locally, you run into a sudden drop in...
Jun 25, 20264 min read0 reactions0 comments
How to Connect Your Local LLM with Web Search Data
This blog will show you how to give a local LLM access to real-time web data. We'll build a small...
Jun 4, 202612 min read0 reactions0 comments
Google Dropped TurboQuant Two Weeks Ago. The Community Already Made It Usable.
Two weeks after Google published their TurboQuant paper at ICLR 2026, five independent implementations exist -- including one running a 104B model on a MacBook. What the community built, what works today, and what it means.
Apr 7, 20266 min read1 reactions0 comments
P
Apr 2, 2026Parameter Count Is the Worst Way to Pick a Model on 8GB VRAM
Parameter Count Is the Worst Way to Pick a Model on 8GB VRAM I've been running local LLMs...
Apr 2, 20265 min read0 reactions0 comments
I
Mar 23, 2026I Pitted 3 Qwen3.5 Models Against Each Other on an RTX 4060 8GB — What Spec Sheets Don't Tell You
I Pitted 3 Qwen3.5 Models Against Each Other on an RTX 4060 8GB — What Spec Sheets Don't...
Mar 23, 20268 min read0 reactions0 comments
Gemma vs. Ollama vs. Local LLMs — Which One Should You Actually Use?
The world of AI is moving at a breakneck pace, and one of the most exciting frontiers for developers...
Jul 22, 20255 min read8 reactions0 comments