LLMGauge guides

Understand local LLM compatibility

Short, source-aware explanations of the memory and runtime concepts behind the calculator.

Explore the guides

Hardware basics

A practical explanation of GPU memory and why it matters when running local language models.

Model basics

Understand how lower-precision weights reduce memory use and introduce quality trade-offs.

Runtime basics

See what it means to run a local model entirely on a GPU, partly on a GPU, or on the CPU.

Runtime basics

Why context length affects memory, how LLMGauge estimates supported KV caches, and what those estimates do not guarantee.

Using LLMGauge

Understand what the calculator checks, how explicit KV-cache estimates affect fit, and where uncertainty remains.