Media
1 item
Description
Will this LLM run on your computer, and how fast? Fit, memory at your context and tokens/sec, on Hugging Face and Ollama. LLM Configurator answers one question on the page where you meet a model: can my computer run this LLM, and how fast? Tell it your graphics card or Mac once. Then every model page it recognises on Hugging Face and Ollama shows: • Fit: Fits, Tight fit, Spills to system RAM, or Too big, for your machine. • Memory at your context length: the model's weights plus the KV cache and overhead at 8K context, or any context you pick in the side panel. Mixture-of-Experts models are sized from all of their parameters, because every expert has to be in memory. • Speed: estimated tokens per second on your machine, shown as a range and labelled ESTIMATED, MEASURED or COMMUNITY. • A better pick for your rig: if a model does not fit, or another ranks higher for what you use AI for, one alternative and the reason. • A run command: a copyable "ollama run" command, only where we have checked that the Ollama tag is this model, and only when it fits. On Hugging Face, a compact card appears under the model header. On ollama.com, which has no fit check, each tag gets a fit and speed chip. The side panel has a Quick check for any model in our library, "What can my rig run?" ranked by use case (chat, coding, reasoning, agents, vision), and your saved rig. Honest when it does not know: a model that is not in our database gets nothing on the page and "Not in our database yet" in the panel. The extension never guesses a size or a speed. Every figure comes from the same engine as llmconfigurator.com, where the formulas are published on the methodology page. Private by design • No account, no sign-in, no analytics, no cookies. • The extension makes no network requests. Model and hardware data ship inside it and are updated with each release. • Your rig is saved in your browser and never leaves your computer. • It reads only huggingface.co and ollama.com pages, to work out which model you are looking at. Privacy policy: https://llmconfigurator.com/en/chrome-extension/privacy More: https://llmconfigurator.com/en/chrome-extension LLM Configurator is independent and is not affiliated with Hugging Face or Ollama.