Launching today
Tag Your Photos
AI-powered keywords for Apple Photos, 100% on your Mac
49 followers
AI-powered keywords for Apple Photos, 100% on your Mac
49 followers
Most AI photo taggers upload your images to the cloud or bolt on as a separate tool. Tag Your Photos doesn't: -100% on-device (Gemma 4 12B via Apple MLX) — no cloud, no upload - Works directly on your Photos library — no exporting, no duplicates - Keywords land in Spotlight system-wide — searchable right from the iPhone/iPad home screen, not just inside the app - Stays general when unsure — no falsely specific guesses
Products used by Tag Your Photos
Explore the tech stack and tools that power Tag Your Photos. See what products Tag Your Photos uses for development, design, marketing, analytics, and more.
Google Gemma 4 12BRun multimodal AI locally with an encoder-free architecture
5.0 (1 review)
Good question! I tested a bunch of model sizes and quantizations against a specific benchmark: correctly identifying Canada geese instead of just labeling them "ducks." Smaller models (~4.5B params) failed that test consistently — even at full precision, no quantization — so it wasn't a quantization issue, it was that they simply don't have enough capacity for fine-grained visual discrimination. Gemma 4 12B at 5-bit was the first one that nailed it reliably, so that became my baseline for TYPh.