whichllmmodel
v1.1.0
Published
Official open-source Hardware & Memory Profiler for whichllmmodel.com - Bridges local hardware into WhichLLM Local Finder
Maintainers
Readme
whichllmmodel
Official Hardware & Memory Profiler for whichllmmodel.com
Inspect your local hardware memory and bridge directly into the whichllmmodel Local Finder.
📦 Quick Start
Run Instantly via npx (No Installation Required)
npx whichllmmodelGlobal Installation
npm install -g whichllmmodel🖥️ Terminal Output Example
whichllmmodel • Hardware & Memory Profiler
Hardware Detected:
• Device: NVIDIA GeForce RTX 3060
• CPU: Intel(R) Core(TM) i7-12700K (win32 x64)
• Architecture: Discrete GPU
Memory Breakdown:
Physical Installed Memory:
• GPU VRAM: 12.0 GB installed
• System RAM: 32.0 GB installed
Live Available Memory (Ready for LLMs):
• GPU VRAM: 10.4 GB available (87% free)
• System RAM: 22.1 GB available (69% free)
Explore all compatible models online:
https://www.whichllmmodel.com/app/text/local?vram=10.4&ram=22.1&memory_mode=available🛠️ CLI Options
| Flag | Description | Example |
| :--- | :--- | :--- |
| -o, --open | Automatically opens the pre-filled Local Finder URL directly in your default browser. | whichllmmodel --open |
# Profile and immediately open WhichLLM Local Finder in browser
whichllmmodel -o📄 License
MIT © whichllmmodel.com
