Show HN: Llmrun – which open LLMs run on your GPU, and how good they are

Category: devtools

Tags: llm, gpu, hardware-compatibility, local-inference

Score: 4.3/10 (Innovation: 4, Technical: 3, Documentation: 2, Utility: 6)

llmrun is a web tool that checks whether a given open LLM can run on a user's GPU by estimating VRAM requirements and expected performance. It addresses a practical pain point for local LLM users, but the provided README is extremely minimal and reveals little about implementation or accuracy.

Target audience: AI/ML practitioners, local LLM enthusiasts, and developers evaluating hardware for model deployment

Repository: https://llmrun.dev

View on Hacker News