Tools and games
AI Hardware Calculator
A web calculator that estimates the memory an open-weight LLM needs, including KV cache across context windows, and checks the fit against GPU VRAM or Apple Silicon unified memory. It covers 8 quantization tiers from Q2_K to FP16, bundles 1,500+ model variants and outputs commands for Ollama, MLX and vLLM.
Overview
Install
-
Clone the repository:
git clone https://github.com/ADM1SH/ai-hardware-calculator.git cd ai-hardware-calculator -
Install dependencies:
npm install -
Start the local development server:
npm run dev -
Open
http://localhost:5173in your browser.
Updates
- docs: update README with comprehensive documentation
- docs: expand README to open source standards
- feat: initial commit for ai hardware calculator
Docs
The full documentation covers how it works, configuration and results.