Skip to content
Convertto

GGUF File Size by Quantisation Level

Work out the download size of a quantised model at every GGUF level, and what quality each one costs you.

A GGUF file is parameters × effective bits per weight ÷ 8. The effective figure is higher than the nominal one because each block of weights carries its own scale — Q4_K_M is 4.83 bits per weight, not 4 — so an 8B model at Q4_K_M is about 4.5 GB rather than 4. This calculator gives the size at all eight common levels with what each costs in quality.

Runs in your browser
Privacy
Runs entirely in your browser — nothing is uploaded
Cost
Free, unlimited, no sign-up

Frequently asked questions

Which quantisation should I download?

Q4_K_M unless you have memory to spare, in which case Q5_K_M or Q6_K. Below Q3 the loss on reasoning and code becomes obvious, and Q2 is rarely worth it — a smaller model at Q4 will usually serve you better.

Why is Q4_K_M bigger than Q4_0 if both are 4-bit?

Because K-quants keep the tensors that matter most — attention and parts of the feed-forward network — at a higher precision than the rest, and carry more per-block metadata. The extra few hundred megabytes buy a measurable quality improvement, which is why Q4_K_M is the community default.

How to use the gguf quantisation size calculator

  1. 1Set the parameters.
  2. 2Choose the quantisation.
  3. 3Turn "Show every level" on or off as needed.
  4. 4The result appears immediately — copy or download it.

Sources & specifications

Embed this tool

Put the working gguf quantisation size calculator on your own site. It runs in your visitors' browsers exactly as it does here — free, no account, nothing uploaded.

Share this tool

Last updated

More ai & llm tools