Performance Tuning
Performance Tuning Ollama and Local LLMs Without Guesswork
09/02/2026
Make Ollama and other local LLM tools feel faster by matching the model, context length, quantization, GPU offload, and logs to the hardware you actually have.
Plex + Tdarr GPU Strategy: Sharing NVIDIA GPUs Without Hurting Playback
06/18/2026
How to share an NVIDIA GPU between Plex and Tdarr without hurting live playback, including worker limits, scheduling, driver checks, and testing.
SABnzbd Performance Tuning for a Homelab Media Server
06/15/2026
Tune SABnzbd for homelab media automation with incomplete folders, connection counts, article cache, Direct Write, categories, priorities, and API checks.