Show HN: Llmspeed – feel how fast a local LLM runs before you buy the hardware
llmspeed.devalbinstman
Llmspeed is an interactive benchmark tool that simulates how different large language models perform on various hardware configurations without requiring users to own the hardware. Users can explore inference speeds across CPUs, GPUs, and other processors to make informed purchasing decisions.
Why it mattersAI practitioners can test if their existing hardware meets their model requirements or validate whether a hardware purchase is worth the cost before committing funds.
Read at llmspeed.dev