LLM Checker

Running LLMs locally, you don't know which sizes your GPU and RAM can handle until a multi-gigabyte download fails. LLM Checker scans your hardware and tells you exactly which LLMs you can run locally.

It recommends models and quantizations with deep Ollama integration, in one command.

Features

Hardware scan:GPU, RAM and CPU.

Recommendations:Sizes and quants.

Ollama:Pull directly.