I made a simple tool to manage llamacpp instances (Metallama)

• Disclaimer*: This post showcase a personnal project. (Free Open Source). Hopefully im not bothering by posting this. I was tired of juggling terminals, manual GGUF downloads and changing inference parameters, so I made a web UI tool for helping doing all that. Here is some cool features (in my opinion): Search and download GGUFs from hugging face api Configure, spawn and monitor llamacpp servers Manage model weights library from the UI Ollama compatible proxy gateway (/ollama) Monitor RAM / VRAM usage of t