REFERENCE
LOOK UP WHAT YOU NEED
Explore definitions and practical reference notes for local AI hardware, models, tools, compatibility, and troubleshooting. Use this index when you need a quick explanation or a detail to support your next step.
LOOK UP WHAT YOU NEED
Explore definitions and practical reference notes for local AI hardware, models, tools, compatibility, and troubleshooting. Use this index when you need a quick explanation or a detail to support your next step.
System RAM is your computer’s working memory. Learn how it supports local AI workloads, how it differs from VRAM, and what to consider when planning memory capacity.
VRAM is the memory used by your GPU. Learn how it affects local AI model capacity, performance, and hardware planning.
A model runner loads and runs AI models on your computer. Learn how it works and how it connects to interfaces and other tools.
Inference is the process of running a trained AI model to generate a result. Learn how it differs from training and what affects local inference performance.
Model quantization reduces memory requirements by using lower-precision values. Learn how it affects local AI model size, output quality, performance, and compatibility.
An AI model needs memory for its weights and working data. Learn how context length, simultaneous requests, and available RAM or VRAM affect whether it can run.