Show HN: Llmspeed – feel how fast a local LLM runs before you buy the hardware

Llmspeed is an interactive tool that simulates how quickly various local language models run on different hardware configurations, allowing users to test performance before purchasing equipment. The platform includes benchmarks across numerous GPU, CPU, and Mac setups paired with popular open-source models like Llama, Qwen, and DeepSeek, with data sourced from community benchmarks and hardware specifications.