Show HN: A GPU/VRAM filter for finding LLMs that will run on your hardware

Category: devtools

Tags: gpu, vram, llm, hardware-filter, comparison-tool

Score: 4.0/10 (Innovation: 4, Technical: 3, Documentation: 2, Utility: 5)

This is a web tool that filters LLM models based on GPU/VRAM constraints, helping users find models that run on their hardware. It's a practical utility for the AI community but lacks technical depth and documentation.

Target audience: AI/ML engineers, data scientists, hobbyists

Repository: https://www.whichllmmodel.com/app/text?local=true

View on Hacker News