VRAM Badge for Your Model Card

Add a “Check VRAM” badge to your Hugging Face model card. It renders a small shields.io button that links readers to a live, per-quantization VRAM breakdown for your model — so “will it run on my GPU?” is one click away.

VRAM Requirements

How to add it

  1. Open your model's model page (or pick it in the generator above).
  2. Copy the Markdown snippet.
  3. Paste it near the top of your model card README.

Example Markdown (for Llama 3.1 8B Instruct):

[![VRAM Requirements](https://img.shields.io/badge/Check_VRAM-LLM_Configurator-blue)](https://llmconfigurator.com/en/models/llama-3-1/llama-3.1-8b?utm_source=badge&utm_medium=referral&utm_campaign=readme_badge&utm_content=llama-3.1-8b)

Popular models