Local-LLM-Launcher-GUI
A browser-based control panel for downloading and running large language models with vLLM or llama.cpp, rating each setting against the user's own hardware so a model launches without hours of trial and error.
Local-LLM-Launcher-GUI is a browser-based control panel for downloading and running local large language models with vLLM or llama.cpp, built on ideas from the vllm-cli project. It targets the frustration of cryptic launch flags and frequent load failures by measuring available memory and adjusting settings automatically.
Every setting is rated green, yellow or red against the user's actual computer and chosen model, with a plain-English explanation and a live status readout showing whether the model will fit before launch; a failed launch is translated into an actionable message. An experimental branch adds SGLang as a fourth engine, though it remains unstable. It needs Python 3.10 or newer and an NVIDIA GPU, Apple Silicon Mac, or enough RAM to run on CPU alone.