Case study
Malcolm Kidd
malcolmkidd.co.uk
Every image in the library re-encoded to AVIF, with WebP behind it and the untouched original behind that. No redesign, no rebuild, and nothing deleted.
less for a visitor to download, measured across 9 pages of the live site.
The heaviest page
Averages hide the page that actually
hurts. On malcolmkidd.co.uk it is /gallery/, which went from
3.3 MB to 1.7 MB —
49.3% lighter. That is the page a visitor on a phone was waiting for.
Page by page
Every page, weighed as a browser loads it
HTML, stylesheets, scripts and images together — not a lab score and not a
projection. Re-runnable at any time, because the page carries both halves of its own
comparison: the AVIF a modern browser takes, and the original still sitting in the
<img> fallback inside it.
| Page | Before | Now | Lighter |
|---|---|---|---|
| Gallery | 3.3 MB | 1.7 MB | 49% |
| Cars vans for sale | 2.4 MB | 538 KB | 78% |
| Testimonials | 1.5 MB | 539 KB | 65% |
| Services | 1.3 MB | 494 KB | 63% |
| Home page | 1.2 MB | 529 KB | 57% |
| Terms conditions | 419 KB | 391 KB | 7% |
| Contact find us | 416 KB | 387 KB | 7% |
| 2016 66 ford transit connect l2 | 411 KB | 382 KB | 7% |
| 2017 66 ford transit connect l1 | 411 KB | 382 KB | 7% |
| Every page | 11.4 MB | 5.2 MB | 54.1% |
The images alone came down 76.1%. The whole-page figure is lower because every page also carries text, layout and code, which this work does not touch — and the whole page is what a visitor waits for, so that is the number quoted at the top. Four of these pages offer several image sizes and the browser picks one by screen width, so those rows read the first candidate rather than a guaranteed download.
What was not done
Nothing was rebuilt, and nothing was thrown away
Originals are untouched
The AVIF and WebP files sit alongside the originals, never over them. Deactivate the plugin and the site serves exactly the bytes it did before, because those bytes never moved.
No browser is left behind
Serving uses <picture>.
Anything that cannot read AVIF takes the WebP, and anything that cannot read either takes
the original. Nobody sees a broken image.
The design did not change
Same theme, same layout, same photographs at the same dimensions. Put this against a screenshot from the week before and it should be indistinguishable.
Want the same measurement on your site?
The analyser fetches your real images and re-encodes them, so the figure you get is yours, not an average.
Test your site