metaai·lightalo unofficial · independent

The Lab

Reading about models is fine. Touching them is better. Everything here is a real Meta model — running in your browser or precomputed on the Raspberry Pi that hosts this site. No cloud calls, no API keys, no tricks.

✂️

Segment Anything

Click any object and the actual SAM mask decoder — 8-bit quantized, running in WebAssembly — cuts it out in real time. The same architecture as Meta's own demo.

model: sam_vit_bruns: in your browserApache 2.0
🌈

How DINOv2 sees

The paper's famous PCA rainbows on our own photos, plus a live patch-matching toy: hover a retriever's ear, light up a dalmatian's.

model: dinov2_vits14runs: precomputed + live JSApache 2.0
🌍

200 languages

Our sentences through NLLB-200's eyes — every FLORES-200 language, every script, instant switching. Then test yourself: guess the language.

model: nllb-200-600Mruns: precomputed on the PiCC-BY-NC
🎵

MusicGen jukebox

Twelve prompts, twelve compositions — sitar sunrises to chiptune arcades — generated by musicgen-small on a Raspberry Pi, with a live spectrogram.

model: musicgen-smallruns: precomputed on the PiCC-BY-NC

How is this possible on a static site?

Big models split naturally into a heavy understanding half and a light interactive half. We run the heavy half once, offline, on a Raspberry Pi 5 (SAM's image encoder, DINOv2's features, NLLB's translations, MusicGen's synthesis) — and ship the light half to you (SAM's 8 MB prompt decoder in WebAssembly, cosine similarity in plain JavaScript). It's the same trick Meta's original Segment Anything demo used in 2023, and it's why a hobby server in Mumbai can hand you a frontier lab's models with zero cloud compute.

Weights belong to their creators; open licenses noted on each page. This site is unofficial and not affiliated with Meta.