Homelab Brief - VRAM Budget: Which LLM Actually Fits Your GPU
The back-of-the-envelope VRAM math for local LLMs: weights, the KV cache everyone forgets, and overhead. Produced with an AI-generated voice; adapted from a Big Iron guide. Full guide: https://www.bigiron.cc/guides/gpu-vram-budget-for-self-hosted-llms-the-2026-model-class-fit
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.