About Fine-tune Calculator

Who runs this

Fine-tune Calculator is built and maintained by Bedino, a small independent web project that makes fast, single-purpose calculators. It is one of a family of tools, each on its own domain, each doing one thing. Contact:[email protected].

What this is

A set of calculators for sizing large-language-model training and serving against real hardware: the GPU memory to fine-tune a model with full, LoRA or QLoRA methods, how to split a model across multiple GPUs, how many concurrent requests a server can hold, whether self-hosting beats an API, and how much disk a checkpoint takes. Its siblingvram-calc.com covers plain inference sizing. No account, no sign-up, no paywall.

How it works

Every calculation runs entirely in your browser. The model, GPU and quantization presets are bundled into the page as plain data — nothing you enter is sent anywhere or stored. The site is deliberately light so pages load fast.

Accuracy

The formulas are standard and stable — parameter counts times bytes per weight, the KV-cache size equation, the memory-bandwidth roofline for decode speed. What ages is the preset data: new models and new GPUs appear constantly. Each tool shows the date its presets were last verified, and every field also accepts fully custom values, so a missing or stale preset never blocks you. The estimates carry a deliberate safety margin; treat them as "fits in practice", not exact minimums. Spotted something wrong or out of date? Tell us at[email protected].

How the site is funded

Fine-tune Calculator is free and paid for by advertising. Ad and analytics scripts load only after you accept via the consent banner — details in theprivacy policy.