Setting up context in a local LLM
Setting up the right context window size is important when configuring a local LLM. Too high, and you will exceed your VRAM, which has performance implications. Too low, and your LLM will not be able to hold enough information at a time to work through problems. Let's talk about how to pick the right number, and how to test the results of our efforts. 00:00 Introduction 01:29 Tokenization 02:43 Measuring VRAM usage 04:09 Setting max context 05:35 Dialing it back 06:34 Real world test: English text 08:11 Real world test: Java code 09:32 Trying with max size 11:30 Summarizing the results 12:02 Next steps 12:26 Outro

▶︎
Automating image tagging with a local LLM

▶︎
Configuring OpenCode for a local LLM

▶︎
Using a local AI for creative writing?

▶︎
We Just Hit the Local LLM Tipping Point (Colibri)

▶︎
Building agents and skills with OpenCode

▶︎
Real-time metaprogramming, zero dependencies // Michael Labbé (Handmade Network Expo 2026)

▶︎
Haskell is DONE

▶︎
192GB of VRAM in One PC… The Cheap Way

▶︎
The Great Bun Rewrite

▶︎
LLM battle 1

▶︎
Android 17 sucks. So I put Linux on a phone.

▶︎
Local AI voice cloning

▶︎
Building llama.cpp from source

▶︎
mattpocock/skills: A complete AI Coding workflow, end-to-end

▶︎
It's Official, The AI Bubble Just Popped (Here's Why)

▶︎
DO NOT BUY: LG’s Spyware TVs, Monitors, and Wiretapping Concerns

▶︎
Count Binface destroys Sky News interviewer

▶︎
The Local AI Hardware Mistake Everyone Makes

▶︎
They Just Built An Impossible Chip

▶︎
