I put a 740M vision model in a browser tab and finally searched my meme folder

Automated excerpt

Startup reads only meta, so a vault of 2,000 memes opens without decoding 2,000 full-size images. It feels like filtering a list, which is the correct feeling. model ready in 57. 1s on webgpu 'a cat' -> cat. jpg (0. 71), 8 hits 'pizza' -> pizza. jpg (0. 73), 8 hits 'the eiffel tower' -> eiffel. jpg (0. 75), 8 hits 'a banana' -> meme-banana. png (0. 77), 8 hits 'a painting of a woman' -> monalisa. jpg (0. 73), 8 hits 'a golden retriever' -> meme-dog. png (0. 75), 8 hits OFFLINE search 'a cat' -> cat. jpg (0.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.