# llmrun > Check which open LLMs run on your GPU and device with VRAM and performance estimates - Website: https://llmrun.dev - Category: AI models & model APIs - Launched on RankRoot: 2026-10-27 - Visitors sent by RankRoot: 0 - Show HN discussion: https://news.ycombinator.com/item?id=50258345 ## About llmrun is an AI model hardware checker that helps users determine which open LLMs can run locally on their GPUs, Macs, or cloud hardware. The platform provides hardware detection, VRAM requirement calculations, expected generation speeds, and aggregated benchmark scores for various open-weight models. ## Who it's for Developers and AI practitioners looking to run large language models locally on their own hardware. ## Use cases - Check GPU compatibility and VRAM requirements for specific open LLMs - Find the best-performing open models for a specific VRAM tier such as 8 GB, 12 GB, 16 GB, 24 GB, or 48 GB - Compare open models using aggregated benchmark scores and composite ratings ## Features - One-click browser-based hardware detection with local processing - Model rankings based on llmrun Composite Score and memory fit - Detailed VRAM estimation covering model weights, KV cache, and overhead - Information on quantization formats like GGUF, token speeds, and context lengths ## FAQ ### What does llmrun do? llmrun checks whether your GPU or device is powerful enough to run a given LLM locally and predicts how fast it will perform. ### Is my hardware data uploaded anywhere? No, hardware detection runs entirely in your browser and nothing is uploaded. ### What file format is used for quantized models? GGUF is the standard file format used for quantized models, bundling weights, tokenizer vocabulary, and metadata into a single file. ### How does llmrun calculate VRAM requirements? llmrun estimates the VRAM footprint by breaking it down into model weights, KV cache, and roughly 0.3 GB of overhead. Source: https://getrankroot.com/launches/llmrun. Product facts come from the maker or the product's own website.