Category Local LLMs

Agents, Local LLMs

Why Hermes Agent Is Eating Your Context Window

I have been playing with custom built agents for a while, mostly for learning purposes, that work with small local LLMs (typically 7b to 35b). But recently I decided to give a change to a bigger open-source agent that opens…

John River
June 19, 2026

Homelab, Local LLMs

ROCm vs Vulkan on the RX 7900 XTX

I benchmarked both llama.cpp backends on a 24GB RX 7900 XTX. The answer isn't "pick one" — it depends entirely on whether your model is dense or MoE.

John River
June 18, 2026