Run serious AI on hardware you own.

Guides to running open models on your own machine: which GPU to buy, which quant to pick, and how fast it will go.

Read the latestBrowse by topic

Start here

The newest guides: how much memory a model takes, and what to run it on.

Local LLM Calculator: Accurate VRAM, RAM & Quantization Sizing Guide

Calculate exact local LLM VRAM and RAM needs. Learn formulas for weights, KV cache, and runtime overhead across quantization tiers and GPU setups.

Guides · · 8 min read

Every claim links to its source. Specs come from the people who make the hardware, numbers from the people who measured them. When sources disagree, we say so.

Browse by topic

1 post

Guides

Latest: Local LLM Calculator: Accurate VRAM, RAM & Quantization Sizing Guide